© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58211
    Prev
    Next
    INDEX
    Explanations

    expletive "shit"

    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_11_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
    ac
    0.38
     Socks
    0.30
    ά
    0.29
     G
    0.28
     E
    0.28
    頊
    0.28
     K
    0.28
     Elevator
    0.27
     TABLE
    0.27
    ोत्
    0.27
    POSITIVE LOGITS
     harbours
    0.26
     trei
    0.25
    டியோ
    0.24
     connotation
    0.23
     rebate
    0.23
    <unused2197>
    0.23
    زاده
    0.23
     மரியாதை
    0.23
    vite
    0.23
    leer
    0.22
    Activations Density 0.002%

    No Known Activations