© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22679
    Prev
    Next
    INDEX
    Explanations

    news

    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
     daily
    0.75
     born
    0.70
     left
    0.68
     Daily
    0.64
    born
    0.63
    daily
    0.61
     DAILY
    0.60
    左
    0.59
     Born
    0.58
    Born
    0.57
    POSITIVE LOGITS
    Head
    0.50
     Head
    0.49
    head
    0.49
     head
    0.46
     हेड
    0.45
    Moment
    0.40
     머
    0.39
    என்
    0.38
     momen
    0.37
    头的
    0.36
    Activations Density 0.007%

    No Known Activations