© 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. 38815
    Prev
    Next
    INDEX
    Explanations

    https, encryption, data, technical jargon

    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
     solvents
    0.61
     ወ
    0.60
    kę
    0.60
     ז
    0.59
    SNL
    0.58
    ISK
    0.57
     denars
    0.57
    㠃
    0.57
     ਨ
    0.56
    docker
    0.55
    POSITIVE LOGITS
    he
    0.72
    цией
    0.70
    is
    0.68
    er
    0.66
    in
    0.65
    man
    0.61
    pieces
    0.57
     favourite
    0.56
     savory
    0.56
    ണ്യ
    0.55
    Activations Density 0.039%

    No Known Activations