© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200949
    Prev
    Next
    INDEX
    Explanations

    professional roles

    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
     difesa
    0.46
     defends
    0.44
     defending
    0.39
    呠
    0.39
    氳
    0.38
     Tengo
    0.38
     Jobs
    0.38
     vutta
    0.37
     hinten
    0.37
     savun
    0.37
    POSITIVE LOGITS
    ጴ
    0.41
    ডে
    0.38
     profesores
    0.38
    ລາ
    0.38
    Teacher
    0.38
    Wrapper
    0.36
    inge
    0.36
    ේෂ
    0.36
    ртов
    0.36
    возмо
    0.36
    Activations Density 0.000%

    No Known Activations