© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42472
    Prev
    Next
    INDEX
    Explanations

    regular expressions and languages

    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_13_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
     interpreters
    0.13
    ῖς
    0.13
    chyné
    0.13
    thisobject
    0.12
     měla
    0.12
    bindingFields
    0.12
    把他
    0.12
    扂
    0.12
     Его
    0.11
     있었다
    0.11
    POSITIVE LOGITS
    se
    0.15
    V
    0.15
    G
    0.15
    g
    0.15
    f
    0.14
    S
    0.14
    in
    0.13
    par
    0.13
    F
    0.13
    Government
    0.13
    Activations Density 0.003%

    No Known Activations