© 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. 90435
    Prev
    Next
    INDEX
    Explanations

    CSS Modules

    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
    a
    0.67
    I
    0.64
    P
    0.64
    i
    0.64
    V
    0.60
    y
    0.59
    \`
    0.57
    ?
    0.56
    !
    0.55
    ERS
    0.55
    POSITIVE LOGITS
    中
    0.63
     produisent
    0.62
    ra
    0.60
    িন
    0.60
     `:`,
    0.60
    ول
    0.60
     afară
    0.60
     aŭ
    0.59
    codes
    0.58
    كان
    0.57
    Activations Density 0.001%

    No Known Activations