© 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. 91642
    Prev
    Next
    INDEX
    Explanations

    document signing tools

    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
    t
    1.10
    d
    1.07
    dür
    0.83
    ll
    0.80
    dig
    0.77
    dx
    0.76
    llä
    0.73
    dl
    0.72
    s
    0.70
    dam
    0.70
    POSITIVE LOGITS
    ன்
    0.77
    ;
    0.75
    ى
    0.74
    い
    0.71
    ir
    0.70
    емых
    0.67
    is
    0.66
    at
    0.66
     year
    0.65
    ipherals
    0.63
    Activations Density 0.000%

    No Known Activations