© 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. 129956
    Prev
    Next
    INDEX
    Explanations

    cdf

    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
    ad
    1.59
    as
    1.42
    O
    1.41
    is
    1.34
    E
    1.32
    ap
    1.30
    و
    1.30
    at
    1.29
    and
    1.29
    was
    1.28
    POSITIVE LOGITS
    t
    1.47
    dě
    1.05
    含ま
    0.96
    ט
    0.96
    tLogRow
    0.95
    '।
    0.95
    鸪
    0.90
    дели
    0.88
    ত্বের
    0.88
    ]。
    0.88
    Activations Density 0.000%

    No Known Activations