© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110339
    Prev
    Next
    INDEX
    Explanations

    kilowatt-hours

    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_2_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
    ↵
    1.37
    ↵↵
    1.19
    ن
    1.19
    ني
    1.04
    /
    0.95
    :
    0.95
    له
    0.91
    -
    0.89
    <0x0D>
    0.89
    ز
    0.89
    POSITIVE LOGITS
    1
    1.52
    the
    1.39
    ма
    1.28
    ک
    1.24
    at
    1.23
    their
    1.21
    າ
    1.21
    ۱
    1.21
    us
    1.20
    ١
    1.20
    Activations Density 0.000%

    No Known Activations