© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34745
    Prev
    Next
    INDEX
    Explanations

    private company

    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_3_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
    t
    0.84
    I
    0.76
    lene
    0.73
    in
    0.73
    er
    0.70
    an
    0.70
    a
    0.70
    ev
    0.68
    T
    0.66
    A
    0.66
    POSITIVE LOGITS
    ){
    0.78
    အတွ
    0.78
    ногда
    0.76
    מ
    0.73
    الي
    0.72
     neuer
    0.72
    其他
    0.71
    اني
    0.71
     anderen
    0.70
     здоровье
    0.70
    Activations Density 0.004%

    No Known Activations