© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32180
    Prev
    Next
    INDEX
    Explanations

    LpVariable('Binary') y

    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
    setFooter
    0.39
    蓽
    0.37
     پرست
    0.36
    茷
    0.36
     보시면
    0.35
    TS
    0.35
     HOSPITAL
    0.35
     perf
    0.34
     விழ
    0.34
     perfused
    0.34
    POSITIVE LOGITS
    ♥
    0.41
    参
    0.39
     descargar
    0.37
     Faye
    0.36
    十三章
    0.35
    '')
    0.35
     ලි
    0.35
    ติดตาม
    0.35
    띵
    0.35
     penjualan
    0.35
    Activations Density 0.016%

    No Known Activations