© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 44219
    Prev
    Next
    INDEX
    Explanations

    student body and aims

    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
    ৭
    0.70
    toare
    0.70
    не
    0.68
    ligere
    0.68
    ة
    0.68
    nicht
    0.66
    ሉም
    0.66
    lichkeit
    0.64
    tahun
    0.63
    dokument
    0.63
    POSITIVE LOGITS
    ın
    0.73
    a
    0.71
     "
    0.69
    </h2>
    0.67
    </h1>
    0.67
    ita
    0.64
    ;
    0.63
    ه
    0.63
    の
    0.63
     .
    0.62
    Activations Density 0.017%

    No Known Activations