© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161649
    Prev
    Next
    INDEX
    Explanations

    dummy files & datasets

    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_31_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
    italizationType
    0.41
    %>
    0.40
     seorang
    0.36
     नाबालिग
    0.36
    %"
    0.36
    LongNumber
    0.36
    搅拌
    0.35
     Dole
    0.35
     diper
    0.35
     மேற்பட்ட
    0.35
    POSITIVE LOGITS
    ifestyles
    0.39
    以來
    0.37
    each
    0.37
     त्याला
    0.37
    囿
    0.36
    since
    0.36
    reading
    0.36
    ్ర
    0.35
    以来
    0.35
    ifiable
    0.35
    Activations Density 0.008%

    No Known Activations