© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105732
    Prev
    Next
    INDEX
    Explanations

    ziplining, Liu Cixin, Weixin

    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
    它
    1.03
    能
    0.95
    発生
    0.93
    可以
    0.89
    ،
    0.86
    ב
    0.86
    會
    0.85
    想到
    0.85
    다
    0.85
    由于
    0.84
    POSITIVE LOGITS
    is
    1.71
    ing
    1.46
    el
    1.46
    ri
    1.44
    al
    1.41
    ang
    1.40
    en
    1.35
    u
    1.35
    m
    1.35
    ant
    1.30
    Activations Density 0.000%

    No Known Activations