© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66242
    Prev
    Next
    INDEX
    Explanations

    torrent websites

    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_41_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
    Ꮽ
    0.43
     Hof
    0.41
    光明
    0.40
     Westminster
    0.39
    ໃ
    0.39
     Pumpkin
    0.38
     Alph
    0.37
    报考
    0.37
    䀠
    0.37
     пога
    0.36
    POSITIVE LOGITS
     torrent
    1.91
     Torrent
    1.73
    Torrent
    1.66
    torrent
    1.64
     тор
    1.23
    Tor
    1.13
     tor
    1.12
     Tor
    1.08
     torrential
    1.08
     TOR
    1.06
    Activations Density 0.004%

    No Known Activations