© 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. 249843
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ഒന്ന്
    0.37
     "~/
    0.37
     Beaumont
    0.36
    呤
    0.35
    blich
    0.35
    [:]
    0.35
     ಹಿಂದೆ
    0.35
     मैकेन
    0.34
     L
    0.34
     mechanical
    0.34
    POSITIVE LOGITS
     देशों
    0.54
     countries
    0.50
     países
    0.50
    countries
    0.50
     Countries
    0.49
    Countries
    0.49
     great
    0.46
     place
    0.45
    Great
    0.45
    place
    0.44
    Activations Density 0.003%

    No Known Activations