© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49079
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    universal
    0.13
    бні
    0.12
     紙
    0.12
    éd
    0.12
    :/
    0.12
    obar
    0.12
    ⎢
    0.12
     ಬಹು
    0.12
    jší
    0.11
    未
    0.11
    POSITIVE LOGITS
     Dynkin
    0.15
     बालों
    0.15
    வினை
    0.15
    ுகிறது
    0.14
     Avenger
    0.14
     سایټ
    0.14
    뀜
    0.14
     ď
    0.14
     می‌کنند
    0.14
     Dude
    0.14
    Activations Density 0.080%

    No Known Activations