© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8773
    Prev
    Next
    INDEX
    Explanations

    code explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ar
    2.52
    ng
    2.43
    ات
    2.41
    нской
    2.30
     contenders
    2.22
    н
    2.18
    لیک
    2.13
    holds
    2.13
    нні
    2.12
    ش
    2.11
    POSITIVE LOGITS
     tekint
    2.69
    @"
    2.57
    boton
    2.44
    การ
    2.42
    ্ধ
    2.36
     homotopy
    2.21
    ف
    2.17
    χου
    2.14
     hostile
    2.08
    يد
    2.07
    Activations Density 0.203%

    No Known Activations