© 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. 7080
    Prev
    Next
    INDEX
    Explanations

    names like Lucky Luciano

    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
    <unused2116>
    0.14
    <unused2137>
    0.13
    ாரம்
    0.13
    <unused2139>
    0.13
    <unused2173>
    0.12
    <unused2157>
    0.12
     mascot
    0.12
    नन
    0.12
    仠
    0.12
    スマス
    0.12
    POSITIVE LOGITS
    roz
    0.12
    loy
    0.12
    je
    0.12
    owner
    0.12
     fit
    0.11
    ended
    0.11
    ori
    0.11
    xe
    0.11
    Orient
    0.11
    aved
    0.11
    Activations Density 0.099%

    No Known Activations