© 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. 148338
    Prev
    Next
    INDEX
    Explanations

    fastapi

    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
     شە
    0.48
    -
    0.44
     ||
    0.43
     ჰ
    0.42
     booties
    0.40
     eruptions
    0.40
     อี
    0.39
     NSUTF
    0.39
     ちゃ
    0.38
     kN
    0.38
    POSITIVE LOGITS
    Det
    0.41
    \-
    0.40
    Most
    0.38
    Su
    0.38
    m
    0.38
    Very
    0.37
    Lib
    0.35
    ٬
    0.35
    With
    0.35
    Sweet
    0.35
    Activations Density 0.001%

    No Known Activations