© 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. 40385
    Prev
    Next
    INDEX
    Explanations

    ongoing development or research

    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
    s
    1.11
    st
    0.76
    cl
    0.76
    D
    0.71
    Call
    0.71
    i
    0.71
    in
    0.70
    ----------------
    0.70
    popup
    0.70
    pending
    0.70
    POSITIVE LOGITS
     guia
    0.77
     quatrième
    0.68
     avión
    0.68
     chín
    0.68
     effluents
    0.66
    önig
    0.66
    ivität
    0.65
     vào
    0.65
     derivados
    0.63
     Natürlich
    0.63
    Activations Density 0.003%

    No Known Activations