© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1601
    Prev
    Next
    INDEX
    Explanations

    say "D" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    Thin
    0.41
    tcpHeader
    0.38
    ၀
    0.38
    rude
    0.38
     manualmente
    0.36
    yfikacja
    0.36
    த்ய
    0.36
     solidaridad
    0.35
    θυν
    0.34
    袒
    0.34
    POSITIVE LOGITS
     figures
    0.55
     cifras
    0.48
     figure
    0.48
     chiffre
    0.46
    figures
    0.46
     chiffres
    0.45
    igenous
    0.41
     숫
    0.41
     фигуры
    0.40
    agi
    0.39
    Activations Density 0.053%

    No Known Activations