© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148660
    Prev
    Next
    INDEX
    Explanations

    tells, lie detection

    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_18_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
    विन
    0.50
    p
    0.46
    ob
    0.43
    已
    0.43
    P
    0.42
     Mailing
    0.41
    TargetPath
    0.41
    x
    0.41
    abd
    0.41
    m
    0.41
    POSITIVE LOGITS
     eukary
    0.49
    ,“
    0.49
     eukaryotes
    0.46
     конден
    0.46
    ভৌম
    0.46
     대부분
    0.46
     конди
    0.46
     condominiums
    0.45
     ATMs
    0.45
     lignin
    0.45
    Activations Density 0.023%

    No Known Activations