© 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. 142539
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or closing parenthesis

    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
    ین
    2.31
    <0x80>
    1.82
    ラ
    1.62
     creciendo
    1.52
    માં
    1.46
    та
    1.32
    UR
    1.31
    ৯
    1.27
     diciendo
    1.26
    ش
    1.24
    POSITIVE LOGITS
     of
    1.30
    1.26
     (
    1.17
    ած
    1.08
    o
    1.07
    柇
    1.05
    舧
    1.05
    et
    1.04
    㑒
    1.04
    ul
    1.03
    Activations Density 0.002%

    No Known Activations