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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165213
    Prev
    Next
    INDEX
    Explanations

    portal

    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_13_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
    ygon
    0.30
    line
    0.28
    geom
    0.27
     &
    0.26
    path
    0.26
     raft
    0.26
    BURY
    0.26
    ileen
    0.25
    ILLA
    0.25
    }$).
    0.25
    POSITIVE LOGITS
     of
    0.27
    cze
    0.26
     moitié
    0.26
    Of
    0.26
     marketed
    0.26
     Of
    0.26
    িত
    0.25
    ccedil
    0.24
     przeci
    0.24
    骸
    0.24
    Activations Density 0.017%

    No Known Activations