© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125945
    Prev
    Next
    INDEX
    Explanations

    extends State

    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_37_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
    <0xF1>
    0.38
    oldsymbol
    0.38
    cmb
    0.37
     Quin
    0.37
    conn
    0.36
    CodeAttribute
    0.36
    plated
    0.36
    gmail
    0.35
    arga
    0.35
     Conn
    0.34
    POSITIVE LOGITS
    zości
    0.42
    駿
    0.40
    ეკ
    0.38
     LOCCTR
    0.37
     explode
    0.37
    の記事
    0.36
    RxDocument
    0.36
     الحره
    0.36
    يدا
    0.36
     exploded
    0.35
    Activations Density 0.000%

    No Known Activations