© 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. 80805
    Prev
    Next
    INDEX
    Explanations

    rotating

    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
    i
    1.52
    that
    1.39
    ни
    1.30
    2
    1.30
    '
    1.27
    <0x80>
    1.23
    <0x0D>
    1.20
    and
    1.16
    z
    1.13
    (
    1.12
    POSITIVE LOGITS
    ס
    1.85
     are
    1.69
    دی
    1.53
    ש
    1.52
    די
    1.49
    ۸
    1.49
    с
    1.48
    ৭
    1.48
    ۹
    1.48
    س
    1.48
    Activations Density 0.000%

    No Known Activations