© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122542
    Prev
    Next
    INDEX
    Explanations

    todo list

    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_37_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
     emisión
    0.37
     서로
    0.37
    激发
    0.36
     Agregar
    0.35
    ("__
    0.35
     Ole
    0.35
    ressione
    0.34
    ifu
    0.34
     Olha
    0.34
     Pada
    0.34
    POSITIVE LOGITS
    ಿದ್ದು
    0.39
     jaar
    0.39
     BUREAU
    0.38
     JACKSON
    0.37
    ZEN
    0.37
    袠
    0.37
    ARRAY
    0.36
     паспо
    0.36
    YEAR
    0.36
    categorical
    0.36
    Activations Density 0.000%

    No Known Activations