© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199276
    Prev
    Next
    INDEX
    Explanations

    specific formatting details

    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_15_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
     Dalai
    0.57
    <unused362>
    0.53
    ח
    0.52
    ay
    0.52
     Eurostile
    0.52
    و
    0.52
     전환
    0.50
     ใช่
    0.50
    vaise
    0.50
     ລັບ
    0.50
    POSITIVE LOGITS
     {
    0.46
     capitalized
    0.46
     narcotics
    0.45
     capital
    0.44
     sheared
    0.43
     depletion
    0.43
     polypeptide
    0.43
     payoffs
    0.42
     muscle
    0.42
     stockp
    0.42
    Activations Density 0.000%

    No Known Activations