© 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. 33935
    Prev
    Next
    INDEX
    Explanations

    paw print

    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
    x
    0.95
    {
    0.73
    M
    0.71
    ot
    0.70
    cliff
    0.70
    v
    0.70
    ne
    0.69
    y
    0.68
    ll
    0.67
    ue
    0.65
    POSITIVE LOGITS
    ের
    0.93
    ת
    0.88
    ی
    0.84
    ей
    0.77
    из
    0.75
    те
    0.75
    ில்
    0.74
    ю
    0.74
    ен
    0.72
    س
    0.72
    Activations Density 0.001%

    No Known Activations