© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176552
    Prev
    Next
    INDEX
    Explanations

    companies and projects

    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_50_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
    商店
    0.46
    ディション
    0.42
     electroneg
    0.41
    lect
    0.40
    尚
    0.38
     Peral
    0.38
     ทอง
    0.37
    త్త
    0.36
    冻
    0.36
    礼
    0.35
    POSITIVE LOGITS
    GraphQl
    0.41
    ej
    0.38
     Almanac
    0.38
    <0x8E>
    0.37
     Verk
    0.37
    aklar
    0.37
    akit
    0.37
    grin
    0.36
     Verz
    0.36
     hyperfine
    0.35
    Activations Density 0.001%

    No Known Activations