© 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. 86203
    Prev
    Next
    INDEX
    Explanations

    file header or component

    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
    ли
    0.72
    साइड
    0.68
     izquier
    0.66
    ુ
    0.66
    yr
    0.65
    り
    0.65
    art
    0.65
    ре
    0.63
    است
    0.63
    ور
    0.62
    POSITIVE LOGITS
     hyperparameters
    0.70
     be
    0.70
     at
    0.70
    i
    0.67
     (
    0.64
     manufactures
    0.63
     prescriptions
    0.63
     for
    0.63
     arguments
    0.62
    t
    0.61
    Activations Density 0.002%

    No Known Activations