© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 60995
    Prev
    Next
    INDEX
    Explanations

    say ')'

    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
     ",
    0.48
     ”,
    0.43
     “,
    0.41
    ",
    0.39
    $",
    0.39
     ".
    0.39
     “.
    0.38
     interesting
    0.37
    (",
    0.37
    ohr
    0.36
    POSITIVE LOGITS
     Mode
    0.54
     Link
    0.54
    -'].
    0.53
     Text
    0.52
    ]&
    0.52
     Course
    0.50
     Sidebar
    0.50
    -/
    0.49
     Texto
    0.49
     Desktop
    0.49
    Activations Density 0.009%

    No Known Activations