© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211533
    Prev
    Next
    INDEX
    Explanations

    code logic

    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_43_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
    ^(
    0.42
    gorod
    0.36
    ('${
    0.36
     vien
    0.35
    沽
    0.35
    shay
    0.35
     बदली
    0.35
    或者是
    0.34
     ayı
    0.34
    ﾕ
    0.34
    POSITIVE LOGITS
    䈤
    0.43
    ƣ
    0.42
    ponses
    0.39
     WrestleMania
    0.38
    emarks
    0.38
     silenc
    0.37
     తీసుకు
    0.36
    ಕ
    0.36
    Listening
    0.35
    群体
    0.35
    Activations Density 0.012%

    No Known Activations