© 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. 41
    Prev
    Next
    INDEX
    Explanations

    code blocks or declarations

    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
     trafficking
    0.49
     traffic
    0.46
    đ
    0.46
     traff
    0.44
     Traffic
    0.43
     tráfico
    0.43
     binary
    0.42
    Bour
    0.40
    bour
    0.39
     Bour
    0.38
    POSITIVE LOGITS
    bě
    0.42
    ㄽ
    0.39
    скопа
    0.38
    scope
    0.36
    ('\\
    0.35
    ზი
    0.35
     inducement
    0.35
    теше
    0.34
    beest
    0.34
    agner
    0.34
    Activations Density 0.001%

    No Known Activations