© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38733
    Prev
    Next
    INDEX
    Explanations

    say "true"

    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_57_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
     cowboys
    0.43
     фраг
    0.42
    Fragment
    0.40
     fragment
    0.39
     friday
    0.39
    Golem
    0.38
     viernes
    0.37
    鄯
    0.37
     plexus
    0.37
     DataSet
    0.37
    POSITIVE LOGITS
    total
    0.43
    tr
    0.42
    TOTAL
    0.41
    il
    0.41
    reporting
    0.39
    PRO
    0.38
    br
    0.37
    im
    0.37
    thr
    0.37
    stir
    0.37
    Activations Density 0.002%

    No Known Activations