© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148016
    Prev
    Next
    INDEX
    Explanations

    win

    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_59_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
    le
    0.54
    cles
    0.47
    cares
    0.46
    cy
    0.45
    care
    0.45
    out
    0.44
    cases
    0.44
    c
    0.44
    че
    0.43
    ceram
    0.43
    POSITIVE LOGITS
     WON
    0.61
     won
    0.55
    Won
    0.52
     Won
    0.52
    WON
    0.52
    нняя
    0.44
    won
    0.44
     wont
    0.42
    γω
    0.42
    就不会
    0.41
    Activations Density 0.000%

    No Known Activations