© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32665
    Prev
    Next
    INDEX
    Explanations

    table definition labels

    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_31_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
     公司
    0.39
    ğmen
    0.37
    ગ
    0.37
     giữ
    0.37
    齣
    0.36
     万元
    0.36
     少
    0.36
    必然
    0.35
    项
    0.35
     लग
    0.35
    POSITIVE LOGITS
    ovin
    0.42
     Ridd
    0.40
    Neutral
    0.39
     Prima
    0.39
    ✓
    0.39
     इक्वेशन
    0.38
    Increasing
    0.38
    延长
    0.38
    Fuse
    0.38
    Rebecca
    0.37
    Activations Density 0.000%

    No Known Activations