© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175979
    Prev
    Next
    INDEX
    Explanations

    health agencies/orgs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    INGLE
    0.41
    ALLED
    0.41
    Bayern
    0.40
    Vi
    0.39
    ница
    0.38
    Cas
    0.37
     fnt
    0.37
    唸
    0.36
    спользу
    0.36
     Orton
    0.36
    POSITIVE LOGITS
     k
    0.60
     KH
    0.60
     ক
    0.58
     Ky
    0.52
     ky
    0.50
     KY
    0.49
    Kyr
    0.49
    KH
    0.48
     Kyr
    0.47
     K
    0.47
    Activations Density 0.000%

    No Known Activations