© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30114
    Prev
    Next
    INDEX
    Explanations

    termination clauses, events, or payments

    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_10_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
    ва
    0.83
    ONG
    0.76
    <0x0D>
    0.75
    アクション
    0.73
    アニメ
    0.72
     titulares
    0.70
    um
    0.70
     oznacza
    0.70
    و
    0.70
    صور
    0.69
    POSITIVE LOGITS
    h
    1.03
     krank
    0.78
    id
    0.75
    ij
    0.75
    ية
    0.74
     terminal
    0.72
    elijk
    0.68
    وم
    0.65
    ט
    0.65
     as
    0.64
    Activations Density 0.010%

    No Known Activations