© 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
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261243
    Prev
    Next
    INDEX
    Explanations

    start of code comments

    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_5_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
    in
    1.80
    t
    1.73
    ان
    1.65
    l
    1.58
    g
    1.54
    ار
    1.44
    is
    1.42
    an
    1.37
    m
    1.32
    ar
    1.30
    POSITIVE LOGITS
     a
    1.45
     o
    1.30
     that
    1.19
    -
    1.16
    ,
    1.05
    ;
    1.05
    5
    1.05
     you
    1.05
    ยัง
    1.02
     av
    0.99
    Activations Density 0.000%

    No Known Activations