© 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. 53714
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    viper
    0.38
    __(
    0.37
    Dialog
    0.37
    走向
    0.36
     megsz
    0.36
    صرية
    0.35
    dataPath
    0.35
    ?’”
    0.35
     Adrienne
    0.35
     Dialog
    0.34
    POSITIVE LOGITS
     মনোনীত
    0.37
    ness
    0.37
     WHETHER
    0.36
    蓖
    0.36
     opinión
    0.35
    Jährige
    0.35
    瞞
    0.35
     iliş
    0.35
     ciddi
    0.34
     cubre
    0.34
    Activations Density 0.000%

    No Known Activations