© 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. 13362
    Prev
    Next
    INDEX
    Explanations

    Ethernet and network cards

    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
     Concerns
    0.50
     Р
    0.48
    َال
    0.48
     Eis
    0.46
     Navigate
    0.46
     चिंता
    0.45
     Cualquier
    0.45
     Porque
    0.45
     Increases
    0.45
     Regarding
    0.45
    POSITIVE LOGITS
    ;
    0.52
     KO
    0.51
    n
    0.50
    l
    0.50
     kampus
    0.48
     SOCKET
    0.48
    ности
    0.48
    mios
    0.47
     softmax
    0.46
    ლებიც
    0.44
    Activations Density 0.049%

    No Known Activations