© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173849
    Prev
    Next
    INDEX
    Explanations

    conversation held

    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_20_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
    市内
    0.45
     क
    0.43
     IC
    0.43
     io
    0.43
     Developmental
    0.43
     BW
    0.43
     valley
    0.42
     int
    0.42
    历
    0.42
     potential
    0.42
    POSITIVE LOGITS
    Banco
    0.46
     Minds
    0.46
    🎧
    0.45
    नावली
    0.45
    ldre
    0.45
    жности
    0.44
    ldef
    0.43
    ‍♂
    0.43
    .”[
    0.42
    larla
    0.42
    Activations Density 0.000%

    No Known Activations