© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30491
    Prev
    Next
    INDEX
    Explanations

    dependent type theory

    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
     chain
    0.47
    チェーン
    0.42
     detect
    0.41
     motivate
    0.40
    pxy
    0.39
     cadeia
    0.39
    链
    0.38
    спе
    0.37
     motivational
    0.37
     lack
    0.37
    POSITIVE LOGITS
    ⤠
    0.41
    යා
    0.37
    Sarah
    0.37
    ಎ
    0.36
    ជ
    0.36
     Andrade
    0.35
    ীবনী
    0.35
     espon
    0.35
    mathop
    0.35
    建議
    0.35
    Activations Density 0.003%

    No Known Activations