© 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. 61957
    Prev
    Next
    INDEX
    Explanations

    same word

    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
    centerX
    0.39
    biz
    0.38
    mtrl
    0.38
    significant
    0.36
    ய்ப்ப
    0.36
    =(
    0.36
    atm
    0.36
    |.
    0.36
     isometry
    0.36
    polygon
    0.35
    POSITIVE LOGITS
     gleichen
    0.52
    Same
    0.50
     Same
    0.48
     radios
    0.47
     même
    0.44
     samma
    0.43
     同じ
    0.41
     same
    0.41
     hetzelfde
    0.41
     palab
    0.40
    Activations Density 0.015%

    No Known Activations