© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80731
    Prev
    Next
    INDEX
    Explanations

    component file paths

    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_0_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
    ون
    1.52
    l
    1.34
    ם
    1.30
    ’।
    1.27
    i
    1.23
    machines
    1.20
    ↵↵↵
    1.14
    in
    1.13
    ก
    1.13
    b
    1.13
    POSITIVE LOGITS
    िंग
    1.36
    其他
    1.36
    し
    1.34
    수
    1.34
    会
    1.30
     về
    1.28
    ш
    1.26
    ме
    1.23
    я
    1.23
    곳
    1.23
    Activations Density 0.000%

    No Known Activations