© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126993
    Prev
    Next
    INDEX
    Explanations

    new words after common ones

    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_3_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
    <0xAB>
    0.71
    för
    0.71
     některé
    0.68
    ot
    0.67
    h
    0.67
    are
    0.66
    گاه
    0.66
    ong
    0.63
    2
    0.62
    é
    0.62
    POSITIVE LOGITS
    க
    0.89
    জ
    0.76
     simulating
    0.73
    д
    0.72
     conifers
    0.70
    ਪ
    0.70
     maladies
    0.70
     destinado
    0.68
    ض
    0.68
     segundo
    0.68
    Activations Density 0.019%

    No Known Activations