© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 30406
    Prev
    Next
    INDEX
    Explanations

    `=` followed by `4`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     whites
    0.53
     white
    0.52
    白
    0.50
     Whites
    0.49
     White
    0.48
    空白
    0.47
     whitespace
    0.46
    whites
    0.45
     白
    0.45
     WHITE
    0.45
    POSITIVE LOGITS
    Bras
    0.36
    TILE
    0.35
     th
    0.34
     fatigue
    0.34
    vä
    0.33
    经纪
    0.33
    Switch
    0.33
    =${
    0.33
    тва
    0.33
     ins
    0.32
    Activations Density 0.002%

    No Known Activations