© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206492
    Prev
    Next
    INDEX
    Explanations

    sleep paralysis, energy conditions, relations, formulas

    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_19_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
     Шев
    0.50
     Екатери
    0.50
     первая
    0.49
    선
    0.49
     Ото
    0.48
     До
    0.48
     возраст
    0.48
     первый
    0.48
     ряд
    0.47
     То
    0.46
    POSITIVE LOGITS
    communications
    0.52
    ي
    0.50
     inadequacy
    0.49
    et
    0.49
     diverging
    0.48
     communications
    0.47
     divergent
    0.47
    i
    0.46
     inade
    0.45
    index
    0.44
    Activations Density 0.000%

    No Known Activations