© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92859
    Prev
    Next
    INDEX
    Explanations

    Parentheses and angle brackets

    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
     const
    0.57
    const
    0.54
     ম
    0.45
    ungere
    0.45
    +
    0.44
    $
    0.43
    èces
    0.42
    ΄
    0.42
    від
    0.41
    THE
    0.41
    POSITIVE LOGITS
    Gw
    0.61
    Json
    0.60
    Common
    0.56
    Jobs
    0.55
     Q
    0.52
    Yuk
    0.50
    Gpio
    0.50
    Ip
    0.50
    Pairs
    0.49
    Kw
    0.49
    Activations Density 0.002%

    No Known Activations