© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211086
    Prev
    Next
    INDEX
    Explanations

    sierra, artefact, menu

    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
    (
    1.28
    س
    1.28
    t
    1.27
    f
    1.23
     on
    1.22
    д
    1.17
    リ
    1.16
    )
    1.13
    ส
    1.13
    ف
    1.13
    POSITIVE LOGITS
    at
    1.22
     밝혔
    1.04
    ون
    1.03
    佚
    0.99
    炲
    0.98
    岃
    0.98
    愭
    0.98
    他不
    0.97
    ่
    0.96
    再加上
    0.95
    Activations Density 0.000%

    No Known Activations