© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77367
    Prev
    Next
    INDEX
    Explanations

    th

    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_53_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
    ៩
    0.43
    𝟏
    0.42
    𝟮
    0.42
     Thành
    0.39
    𝟎
    0.39
    ៣
    0.39
    𝟐
    0.39
    𝐖
    0.39
    ៥
    0.38
    ０
    0.38
    POSITIVE LOGITS
    endimento
    0.36
    🜨
    0.36
    ριά
    0.35
    eldorf
    0.34
    ياء
    0.34
    essie
    0.34
    рія
    0.34
    raising
    0.33
     khúc
    0.33
    ército
    0.33
    Activations Density 0.001%

    No Known Activations