© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36929
    Prev
    Next
    INDEX
    Explanations

    coronel, SDK, intervention, discharge

    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_3_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
    ly
    0.70
    <
    0.68
    li
    0.60
    ynch
    0.54
    !
    0.54
    ian
    0.53
    nél
    0.50
    야
    0.50
    ole
    0.49
    ский
    0.49
    POSITIVE LOGITS
    ه
    1.02
    ா
    0.98
    ב
    0.97
    ה
    0.92
    ে
    0.86
    in
    0.85
    ي
    0.85
    ма
    0.85
    es
    0.83
    س
    0.80
    Activations Density 0.001%

    No Known Activations