© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48535
    Prev
    Next
    INDEX
    Explanations

    line number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    U
    0.37
    T
    0.34
    TNF
    0.33
    AS
    0.33
    LE
    0.31
    THAT
    0.31
    Zombie
    0.30
    ﺼ
    0.30
    ↵
    0.30
    ST
    0.30
    POSITIVE LOGITS
    s
    0.37
    ية
    0.34
     errores
    0.33
    ators
    0.33
    də
    0.31
    ed
    0.31
    atical
    0.31
    ות
    0.30
    n
    0.30
    ség
    0.29
    Activations Density 0.056%

    No Known Activations