© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125014
    Prev
    Next
    INDEX
    Explanations

    Substack chat posts

    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_3_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
    -
    0.81
    ни
    0.76
    ə
    0.75
    <0x0D>
    0.68
    0.67
    0.66
    ";
    0.66
    ב
    0.64
    )=
    0.63
    ън
    0.62
    POSITIVE LOGITS
     in
    0.71
    在
    0.65
    もら
    0.62
    吭
    0.62
    螌
    0.62
     scherm
    0.61
    도
    0.60
    不足
    0.59
     माध्यम
    0.59
     در
    0.59
    Activations Density 0.000%

    No Known Activations