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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261347
    Prev
    Next
    INDEX
    Explanations

    operating agreement distribution binary

    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_5_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
    {
    1.17
    我
    1.15
    1.07
    <
    1.02
    !
    1.01
    }{
    0.99
    Cas
    0.98
    .
    0.97
    ס
    0.96
    Від
    0.96
    POSITIVE LOGITS
     by
    1.39
    ’
    1.30
    ים
    1.17
    ों
    1.13
    یی
    1.13
    as
    1.06
    at
    1.05
    ی
    1.04
    та
    1.02
    ิ
    1.01
    Activations Density 0.000%

    No Known Activations