© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231795
    Prev
    Next
    INDEX
    Explanations

    Marvel Cinematic Universe

    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_6_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
    ed
    1.59
    an
    1.41
    ing
    1.34
    as
    1.34
    T
    1.30
    al
    1.30
    il
    1.30
    on
    1.27
    ’
    1.25
    er
    1.23
    POSITIVE LOGITS
     Сер
    1.17
     Фе
    1.13
     Фер
    1.08
    GTBase
    1.08
    PlayerDataCache
    1.05
     Ве
    1.05
     Фа
    1.05
    xcuser
    1.03
    <unused511>
    1.02
    <unused434>
    1.02
    Activations Density 0.000%

    No Known Activations