© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204937
    Prev
    Next
    INDEX
    Explanations

    discovered, found, proposed, proved, argued

    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_25_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
     موا
    0.40
    each
    0.36
     জাতি
    0.35
    ্যারি
    0.35
    ෲ
    0.35
    profits
    0.34
     усі
    0.34
     ആശയ
    0.34
     অপার
    0.33
     лише
    0.33
    POSITIVE LOGITS
     दिनों
    0.43
     denominators
    0.38
    ilogue
    0.38
    ছের
    0.37
    <span>
    0.36
     éve
    0.36
    预览
    0.36
    ך
    0.36
     የ
    0.35
    ંક
    0.35
    Activations Density 0.001%

    No Known Activations