© 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. 46483
    Prev
    Next
    INDEX
    Explanations

    division and equations

    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
     měla
    0.12
     NES
    0.11
    ッ
    0.11
     ETFs
    0.11
     Decre
    0.11
    奘
    0.10
     DDT
    0.10
     Increases
    0.10
    </td>
    0.10
    </i>
    0.10
    POSITIVE LOGITS
    W
    0.13
    -【
    0.11
    I
    0.11
    E
    0.11
    ISE
    0.11
    At
    0.11
    Riley
    0.11
    In
    0.11
    L
    0.11
    Brit
    0.10
    Activations Density 0.068%

    No Known Activations