© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213489
    Prev
    Next
    INDEX
    Explanations

    code explanation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    仕様
    0.37
     esperamos
    0.36
     deals
    0.36
     weak
    0.36
    腊
    0.34
    াইল
    0.33
    ेंसी
    0.33
    RequestListener
    0.33
     ens
    0.33
     বলা
    0.32
    POSITIVE LOGITS
     à
    0.94
    à
    0.67
     À
    0.57
    À
    0.53
     á
    0.46
    character
    0.44
    To
    0.44
    At
    0.43
    ICreate
    0.43
     به
    0.41
    Activations Density 0.017%

    No Known Activations