© 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. 38681
    Prev
    Next
    INDEX
    Explanations

    visceral, visually, vicious

    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
    "
    0.66
     CHE
    0.60
    Ws
    0.59
    ',
    0.59
     exploits
    0.59
     ro
    0.57
     quilts
    0.57
     t
    0.56
     R
    0.56
     tr
    0.56
    POSITIVE LOGITS
    ni
    0.71
     براي
    0.68
    liğini
    0.66
     sonuç
    0.63
    für
    0.63
    läuft
    0.62
     an
    0.60
    ness
    0.60
     dinámica
    0.59
     başına
    0.58
    Activations Density 0.001%

    No Known Activations