© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28394
    Prev
    Next
    INDEX
    Explanations

    they did or took

    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_10_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
    il
    0.28
    on
    0.22
     for
    0.20
     on
    0.19
    ap
    0.19
     A
    0.18
    ut
    0.18
    ila
    0.17
    ↵↵
    0.17
    ig
    0.17
    POSITIVE LOGITS
    ों
    0.23
    ς
    0.23
    ओं
    0.23
    ی
    0.22
     água
    0.21
    s
    0.20
    к
    0.20
    ﺧ
    0.19
    <0x0D>
    0.19
     ángulos
    0.18
    Activations Density 0.000%

    No Known Activations