© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    cancer, disease, history, grade, GPT

    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
    as
    0.15
    v
    0.15
    V
    0.14
    象
    0.13
     purify
    0.13
    z
    0.13
    that
    0.12
    p
    0.12
     purifying
    0.12
    wait
    0.12
    POSITIVE LOGITS
     Очень
    0.17
     இன்
    0.17
    Очень
    0.16
     очень
    0.16
     novembre
    0.16
     жест
    0.16
     Интер
    0.16
    aço
    0.16
     wodurch
    0.16
     редак
    0.16
    Activations Density 0.029%

    No Known Activations