© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83060
    Prev
    Next
    INDEX
    Explanations

    rated

    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_0_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
    ри
    1.85
    ים
    1.84
    ی
    1.82
    ের
    1.77
    ও
    1.68
    ки
    1.66
    も
    1.65
    ో
    1.60
    ો
    1.55
    ী
    1.54
    POSITIVE LOGITS
     a
    1.73
    st
    1.66
    don
    1.56
    f
    1.50
     as
    1.47
    be
    1.41
    it
    1.38
    வ்வேறு
    1.35
    as
    1.33
    dans
    1.30
    Activations Density 0.001%

    No Known Activations