© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203383
    Prev
    Next
    INDEX
    Explanations

    code or programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ソ
    0.51
     SER
    0.44
     ソ
    0.44
     sopa
    0.44
     Sé
    0.44
     sola
    0.43
     sé
    0.42
     Serr
    0.42
     spn
    0.42
     scooter
    0.42
    POSITIVE LOGITS
    nich
    0.42
    참
    0.40
     referring
    0.38
    Aq
    0.38
    čno
    0.38
    Citizen
    0.38
    Adm
    0.37
    Bi
    0.36
    цов
    0.36
    Chat
    0.36
    Activations Density 0.000%

    No Known Activations