© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150436
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     Function
    0.50
    “.
    0.48
    ').
    0.48
     “.
    0.43
    ”.
    0.43
    ".[
    0.42
    ").
    0.42
    ).[
    0.40
     Cancer
    0.40
     Kafka
    0.40
    POSITIVE LOGITS
    math
    0.49
     IR
    0.49
     IRR
    0.48
     math
    0.47
     आरआर
    0.47
    ℂ
    0.45
     MATH
    0.44
    rir
    0.44
    nR
    0.43
    *",
    0.42
    Activations Density 0.002%

    No Known Activations