© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139284
    Prev
    Next
    INDEX
    Explanations

    Nikola Jokic and Bobby Moore

    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_12_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
     you
    0.55
    ল
    0.51
    kkal
    0.50
    You
    0.49
    匚
    0.49
    AMA
    0.49
    Pel
    0.48
    Hard
    0.48
    른
    0.48
    Jaw
    0.47
    POSITIVE LOGITS
    וס
    0.54
    oros
    0.52
    ाना
    0.49
    matic
    0.48
    गरानी
    0.48
     contempla
    0.48
     Ανα
    0.48
    স্ত্র
    0.47
    ories
    0.47
    ితి
    0.45
    Activations Density 0.000%

    No Known Activations