© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61203
    Prev
    Next
    INDEX
    Explanations

    rejecting responsibility or association

    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
    ر
    0.70
     MacOS
    0.69
    от
    0.68
    я
    0.64
     Qualitäts
    0.63
    ان
    0.63
     تغییر
    0.62
    ა
    0.62
     Reprinted
    0.62
    Termination
    0.61
    POSITIVE LOGITS
     vremena
    0.58
    alon
    0.54
     учё
    0.54
     worst
    0.54
     In
    0.54
     in
    0.51
    ía
    0.51
     einz
    0.51
     inexplic
    0.51
     so
    0.51
    Activations Density 0.003%

    No Known Activations