© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 666
    Prev
    Next
    INDEX
    Explanations

    JOIN semantic_ecommerce.orders AS o ON c.c_custkey = o.o_custkeyJOIN Employee AS T2 ON T1.employee_id = T2.idJOIN policy_clause AS pc ON ip.policy_number = pc.policy_numberJOIN DoctorDetails AS T2 ON T1.DoctorID = T2.DoctorIDJOIN products AS p ON o.product_id = p.product_idJOIN HospitalData AS HD ON DD.DoctorID = HD.DoctorIDINNER JOIN has_pet AS T2 ON T1.stuid = T2.stuidJOIN insurance_application AS ia ON ip.application_number = ia.application_numberINNER JOIN takes AS T2 ON T1.ID = T2.IDJOIN Artist AS T2 ON T1.ArtistId = T2.ArtistId

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    infi
    0.32
     relativi
    0.31
     inflex
    0.30
    icznego
    0.29
    anzas
    0.28
    íe
    0.28
     coax
    0.28
    ƴ
    0.28
    AuthConfig
    0.27
     jatuh
    0.27
    POSITIVE LOGITS
    ESIS
    0.29
     пам
    0.28
     অংশগ্রহণ
    0.28
     subsystem
    0.28
     cm
    0.28
     realisation
    0.28
     pomo
    0.27
     sampler
    0.27
    晛
    0.27
     nullptr
    0.27
    Activations Density 0.001%

    No Known Activations