© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 3954
    Prev
    Next
    INDEX
    Explanations

    new project creation

    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_38_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
     banded
    0.42
     pink
    0.40
     banding
    0.39
     lắc
    0.39
     Task
    0.38
     logger
    0.38
    盱
    0.38
     Bid
    0.38
     elite
    0.37
     mark
    0.36
    POSITIVE LOGITS
    Bab
    0.43
    bromo
    0.42
    Baba
    0.41
    Shiny
    0.41
    references
    0.40
    Trail
    0.40
    稒
    0.39
    Einstein
    0.39
    斻
    0.39
    Eat
    0.39
    Activations Density 0.025%

    No Known Activations