© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104542
    Prev
    Next
    INDEX
    Explanations

    title tags and attributes

    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_1_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
    ח
    1.05
    وا
    0.95
    ها
    0.91
    ר
    0.89
    ల
    0.87
    p
    0.86
    در
    0.83
    the
    0.82
    רק
    0.81
    р
    0.81
    POSITIVE LOGITS
    ки
    0.86
     continu
    0.85
     and
    0.83
    ﻗ
    0.83
     puddle
    0.82
    <h4>
    0.78
     \
    0.77
    ็ต
    0.77
     resale
    0.76
     gout
    0.74
    Activations Density 0.001%

    No Known Activations