© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43359
    Prev
    Next
    INDEX
    Explanations

    past usage and timeframes

    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
     interés
    0.84
    is
    0.79
    ミス
    0.75
     cięż
    0.73
     broni
    0.72
     preço
    0.71
    t
    0.71
    ланти
    0.70
    利
    0.70
    ње
    0.69
    POSITIVE LOGITS
     a
    0.98
    9
    0.84
    {
    0.79
    1
    0.78
    ba
    0.77
    \%
    0.75
    ;
    0.70
    4
    0.68
    da
    0.66
    3
    0.65
    Activations Density 0.008%

    No Known Activations