© 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. 52886
    Prev
    Next
    INDEX
    Explanations

    warning message/error message

    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
     시장
    0.39
    빨
    0.37
    indicating
    0.36
     răsp
    0.36
    indication
    0.35
     ответ
    0.35
     온라인
    0.35
    消费
    0.34
    재
    0.34
     метра
    0.33
    POSITIVE LOGITS
    Hitpoint
    0.36
    igueur
    0.35
    ิตร
    0.35
    YW
    0.35
    ৌক
    0.35
     maraming
    0.34
     CM
    0.34
     Leser
    0.34
    洵
    0.34
    juang
    0.34
    Activations Density 0.004%

    No Known Activations