© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199890
    Prev
    Next
    INDEX
    Explanations

    Multi Jet Fusion cards

    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_12_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
    perturbative
    0.52
    resources
    0.50
     такой
    0.48
    Submission
    0.48
     میک
    0.46
    ૂ
    0.46
    Essex
    0.46
    trails
    0.45
    مان
    0.45
     such
    0.45
    POSITIVE LOGITS
    cdZ
    0.54
     privata
    0.54
     ...)
    0.50
     miglior
    0.50
     लाइस
    0.50
     poem
    0.49
     Lawyers
    0.48
     cinese
    0.48
     *)
    0.47
     _)
    0.47
    Activations Density 0.001%

    No Known Activations