© 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. 62331
    Prev
    Next
    INDEX
    Explanations

    thank you, appreciated

    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
    ’
    0.67
     chiều
    0.62
     fiancé
    0.61
    ר
    0.61
     la
    0.60
    ρα
    0.60
    μή
    0.60
     её
    0.60
    内的
    0.60
    的选择
    0.60
    POSITIVE LOGITS
    o
    0.67
    the
    0.62
     ਸਿੰਘ
    0.57
     offizi
    0.55
    ES
    0.53
     InputDecoration
    0.52
     logiciels
    0.52
    <unused61>
    0.51
    from
    0.51
    waitFor
    0.51
    Activations Density 0.001%

    No Known Activations