© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90051
    Prev
    Next
    INDEX
    Explanations

    Laz

    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_60_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
    y
    0.93
     erz
    0.48
    𝙮
    0.47
     ز
    0.46
     zelo
    0.45
    <0xA1>
    0.45
     y
    0.44
     BRAD
    0.44
     herunter
    0.44
     maß
    0.43
    POSITIVE LOGITS
    at
    0.57
    is
    0.54
    last
    0.49
    iselle
    0.45
    "
    0.44
    name
    0.44
    Do
    0.43
    iate
    0.43
    Qu
    0.43
    aver
    0.42
    Activations Density 0.000%

    No Known Activations