© 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. 126751
    Prev
    Next
    INDEX
    Explanations

    code blocks or formulas

    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
    शीलता
    0.39
    ృతి
    0.38
    味料
    0.38
     رپور
    0.37
    ሪ
    0.36
    راء
    0.36
    šť
    0.36
     रिक
    0.36
     certaines
    0.35
     besucht
    0.34
    POSITIVE LOGITS
     \...
    0.36
     ...
    0.34
     cottage
    0.34
     Redist
    0.33
    innest
    0.33
    .$(
    0.32
     studente
    0.32
    ələ
    0.32
     অন্
    0.31
     Pash
    0.31
    Activations Density 0.043%

    No Known Activations