© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 62005
    Prev
    Next
    INDEX
    Explanations

    the more

    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_11_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
    tobago
    0.66
    otheby
    0.60
    Kis
    0.58
    Ř
    0.57
    osomal
    0.56
    går
    0.56
    াদান
    0.55
     கலை
    0.55
    filtration
    0.55
    esthetics
    0.55
    POSITIVE LOGITS
    ne
    0.74
     a
    0.63
    的な
    0.61
     provinc
    0.60
    な
    0.57
     que
    0.56
     f
    0.56
     be
    0.55
     npc
    0.54
    كه
    0.54
    Activations Density 0.006%

    No Known Activations