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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231228
    Prev
    Next
    INDEX
    Explanations

    regex character sets

    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_6_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
    ih
    0.98
    ہ
    0.87
    ineas
    0.86
    ine
    0.83
     in
    0.82
    è
    0.82
    IN
    0.80
     burglary
    0.80
    iney
    0.79
    ép
    0.79
    POSITIVE LOGITS
    arza
    1.21
    that
    1.13
    ar
    1.02
    ۹
    1.01
     that
    0.99
    arın
    0.93
    arının
    0.92
    an
    0.89
    to
    0.88
    ת
    0.88
    Activations Density 0.000%

    No Known Activations