© 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. 36936
    Prev
    Next
    INDEX
    Explanations

    Highsmith, Varible, Elastic, Hyperforce

    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
     exposé
    0.73
    k
    0.73
     أ
    0.72
     असंभव
    0.64
     be
    0.63
     و
    0.63
     οποίο
    0.62
     environ
    0.61
    ுள்ளார்
    0.61
     über
    0.60
    POSITIVE LOGITS
    a
    0.93
    is
    0.86
    <0x0D>
    0.86
    as
    0.83
    т
    0.82
    ig
    0.82
    ه
    0.82
    an
    0.81
    es
    0.79
    ш
    0.79
    Activations Density 0.005%

    No Known Activations