© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5456
    Prev
    Next
    INDEX
    Explanations

    match

    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_39_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
    由
    0.37
    빚
    0.35
    적인
    0.34
    鼐
    0.33
     由
    0.33
     બના
    0.32
    ད
    0.32
     교수
    0.32
    뜯
    0.32
    璀
    0.31
    POSITIVE LOGITS
    match
    0.51
     matches
    0.50
    マッチ
    0.50
     match
    0.50
    MATCH
    0.48
     MATCH
    0.45
     matching
    0.44
    Matches
    0.44
    Match
    0.43
     Match
    0.41
    Activations Density 0.001%

    No Known Activations