© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144033
    Prev
    Next
    INDEX
    Explanations

    monk

    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
    с
    2.09
    لي
    1.95
    、
    1.88
    ない
    1.52
    て
    1.50
    ،
    1.48
    ும்
    1.46
    س
    1.45
    ス
    1.44
    <0xF3>
    1.43
    POSITIVE LOGITS
    d
    2.23
    b
    2.22
    c
    1.94
    p
    1.67
    H
    1.64
    s
    1.63
    on
    1.61
    g
    1.59
    R
    1.50
    y
    1.47
    Activations Density 0.000%

    No Known Activations