© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89117
    Prev
    Next
    INDEX
    Explanations

    attr() function calls

    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_3_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
     I
    0.86
    م
    0.81
    ↵
    0.80
     semifinals
    0.76
     étend
    0.73
    ری
    0.70
    ルフ
    0.70
    のア
    0.70
    ই
    0.70
    ль
    0.68
    POSITIVE LOGITS
    ’
    1.30
    '
    1.09
    س
    1.05
    on
    0.96
    us
    0.87
    с
    0.80
    5
    0.78
    1
    0.77
    (
    0.75
    jack
    0.73
    Activations Density 0.000%

    No Known Activations