© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105089
    Prev
    Next
    INDEX
    Explanations

    reply with context

    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
    ي
    1.18
    ા
    0.98
    </h4>
    0.97
    د
    0.97
    '
    0.96
    া
    0.95
    ه
    0.93
    </h3>
    0.88
    <0x0D>
    0.86
    는
    0.86
    POSITIVE LOGITS
    ed
    1.11
    at
    1.07
    ized
    1.04
    en
    1.02
    am
    0.96
    ys
    0.95
    ak
    0.94
    ation
    0.88
    ering
    0.88
    ↵↵
    0.88
    Activations Density 0.004%

    No Known Activations