© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36051
    Prev
    Next
    INDEX
    Explanations

    foul-mouthed

    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_3_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
     maxim
    0.64
    ة
    0.63
     fals
    0.63
    ம்
    0.61
    ின்
    0.61
     cámara
    0.61
     falsa
    0.61
     menyiapkan
    0.61
     lê
    0.57
     FTE
    0.57
    POSITIVE LOGITS
    an
    1.18
    t
    1.03
    H
    1.03
    د
    1.02
    R
    1.00
    L
    0.97
    S
    0.95
    im
    0.93
    P
    0.93
    D
    0.92
    Activations Density 0.002%

    No Known Activations