© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209688
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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_20_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
    <{},
    0.32
    ந
    0.31
    ?,?,
    0.30
    Outputs
    0.30
    ccbp
    0.30
    وال
    0.30
    その他の
    0.30
    وده
    0.30
    !\!\
    0.29
    inheritdoc
    0.29
    POSITIVE LOGITS
    isOnTimer
    0.40
     ലോ
    0.38
    在一个
    0.33
     št
    0.32
     τε
    0.32
     ஓ
    0.31
     tranh
    0.31
    אם
    0.31
     라
    0.31
     চারি
    0.31
    Activations Density 0.002%

    No Known Activations