© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 153032
    Prev
    Next
    INDEX
    Explanations

    say "isalnum"

    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
     .,
    0.40
    ?,
    0.37
    *;
    0.36
    ...,
    0.35
    '$,
    0.35
    ються
    0.34
     **,
    0.34
    !।
    0.34
    [],
    0.33
     нравится
    0.33
    POSITIVE LOGITS
     Casting
    0.34
    casting
    0.33
     casting
    0.30
     Post
    0.29
     Cloning
    0.29
     Reading
    0.29
    watching
    0.28
     Scales
    0.28
     CAPS
    0.28
     Evaluating
    0.27
    Activations Density 0.000%

    No Known Activations