© 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. 46238
    Prev
    Next
    INDEX
    Explanations

    names and titles following them

    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
    '
    1.30
    -
    0.91
    (
    0.89
    "
    0.85
    '*
    0.79
    h
    0.78
     OF
    0.76
    ية
    0.74
    '')
    0.74
    /
    0.73
    POSITIVE LOGITS
    ین
    0.90
    𝘀
    0.84
    ای
    0.71
    اد
    0.71
    مانی
    0.71
    in
    0.69
    نق
    0.66
     مشینیں
    0.66
    म्स
    0.65
    un
    0.65
    Activations Density 0.001%

    No Known Activations