© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57210
    Prev
    Next
    INDEX
    Explanations

    falls under

    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_11_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
    த்துள்ளது
    0.54
     novoProduto
    0.54
     குறிப்பிட்ட
    0.53
     ASH
    0.52
    🏪
    0.52
    භාව
    0.52
     იყო
    0.52
    甃
    0.51
     depicts
    0.51
     dBASE
    0.51
    POSITIVE LOGITS
    R
    0.61
    I
    0.58
    ER
    0.57
    U
    0.57
    OF
    0.54
    A
    0.53
    er
    0.52
    AM
    0.50
    S
    0.50
    AT
    0.50
    Activations Density 0.013%

    No Known Activations