© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206802
    Prev
    Next
    INDEX
    Explanations

    vomiting

    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_56_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
    恶
    0.45
     Zeb
    0.41
     Moul
    0.41
     Foreign
    0.40
     mentally
    0.40
    Foreign
    0.39
    扔
    0.38
     unknow
    0.38
     lured
    0.38
    悪
    0.37
    POSITIVE LOGITS
    ADAS
    0.43
    PSK
    0.43
    BCD
    0.39
    ATED
    0.39
    ITY
    0.38
    ANDS
    0.38
    IT
    0.38
    লাস
    0.38
    ARY
    0.37
    idis
    0.37
    Activations Density 0.000%

    No Known Activations