© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204431
    Prev
    Next
    INDEX
    Explanations

    the

    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_56_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
    outside
    0.40
    餸
    0.37
    평
    0.34
    इसके
    0.33
    ATTR
    0.33
    वाट
    0.33
    dataSet
    0.33
    󰡕
    0.33
    ewnątrz
    0.33
    অনু
    0.33
    POSITIVE LOGITS
     whole
    0.97
     entire
    0.93
     ganze
    0.79
    Whole
    0.78
     în
    0.76
    whole
    0.75
     hele
    0.75
     Whole
    0.74
     hela
    0.73
    整个
    0.72
    Activations Density 0.002%

    No Known Activations