© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    light color wavelengths

    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
    ัฒ
    0.45
    lbrakk
    0.41
    irikan
    0.39
     এমনকি
    0.38
     thậm
    0.38
     Everglades
    0.37
    even
    0.37
    崭
    0.37
    rops
    0.37
     Bew
    0.37
    POSITIVE LOGITS
     hues
    0.39
     Refund
    0.39
     средней
    0.39
    स्‍त
    0.39
     օ
    0.38
     insoluble
    0.38
    ۥ
    0.38
     rápidos
    0.38
     todas
    0.37
     Highest
    0.37
    Activations Density 0.142%

    No Known Activations