© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130787
    Prev
    Next
    INDEX
    Explanations

    cause or cases

    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_1_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
    P
    1.13
    ي
    1.12
    i
    1.09
    A
    1.08
    Y
    1.07
    ون
    1.04
    D
    1.04
    W
    1.00
    ك
    1.00
    ۔
    0.98
    POSITIVE LOGITS
    0
    1.52
    <0x80>
    1.00
     to
    0.92
    ang
    0.92
    лось
    0.90
    ू
    0.89
     you
    0.89
    ся
    0.89
    ₀
    0.89
    larının
    0.88
    Activations Density 0.000%

    No Known Activations