© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14938
    Prev
    Next
    INDEX
    Explanations

    section numbers and chapter titles

    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_34_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
    栖
    0.38
     figure
    0.37
     entering
    0.36
    entering
    0.35
    FIGURE
    0.35
    racting
    0.34
     Noi
    0.34
     alien
    0.34
     suo
    0.33
    Figure
    0.33
    POSITIVE LOGITS
     의미
    0.38
    Fine
    0.38
    绪
    0.37
     உள்ளது
    0.37
    Slope
    0.37
    Entire
    0.36
    ৃত্বে
    0.36
    BorderStyle
    0.36
    Fix
    0.35
    defeated
    0.35
    Activations Density 0.018%

    No Known Activations