© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207202
    Prev
    Next
    INDEX
    Explanations

    capability and potential

    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_19_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
    www
    0.56
     www
    0.51
    (
    0.46
     Holy
    0.45
    ¡
    0.44
     Sign
    0.43
    /
    0.43
    <
    0.43
    -
    0.43
    Cl
    0.42
    POSITIVE LOGITS
    buttonLevel
    0.48
    вершена
    0.46
    ঞ্জেল
    0.46
     bodhis
    0.45
     samurai
    0.45
     carpenters
    0.44
    angleright
    0.44
    ómago
    0.43
     モン
    0.43
    ້າງ
    0.43
    Activations Density 0.000%

    No Known Activations