© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87394
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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_23_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
    蕉
    0.22
     Chief
    0.22
    州市
    0.21
    告诉你
    0.21
    多家
    0.21
    解答
    0.20
     држа
    0.20
    zień
    0.20
     railroad
    0.20
    মুখ
    0.20
    POSITIVE LOGITS
     sıv
    0.23
    ='
    0.23
     हमने
    0.23
     យើង
    0.23
     putea
    0.22
     microbes
    0.22
    ('
    0.22
     FF
    0.22
    ของเรา
    0.22
     (&
    0.22
    Activations Density 0.000%

    No Known Activations