© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62966
    Prev
    Next
    INDEX
    Explanations

    start timing

    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_41_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
    Binding
    0.43
    bicyclo
    0.42
     binding
    0.40
     Binding
    0.39
     bindings
    0.38
    Ⅴ
    0.36
     peace
    0.36
     hip
    0.36
    ժ
    0.35
    ylon
    0.34
    POSITIVE LOGITS
     W
    0.66
     CW
    0.63
    CW
    0.63
    cw
    0.51
    W
    0.50
     cw
    0.49
     डब्ल्यू
    0.47
     ال
    0.46
     WIB
    0.44
    WAM
    0.43
    Activations Density 0.000%

    No Known Activations