© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93504
    Prev
    Next
    INDEX
    Explanations

    7 runs

    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
    ie
    0.68
    n
    0.66
    ing
    0.62
     e
    0.62
     Sel
    0.61
     Farming
    0.60
    theit
    0.60
     Sound
    0.59
    ies
    0.57
     Teams
    0.57
    POSITIVE LOGITS
    UNIVERSITY
    0.54
    로
    0.52
     incorrectly
    0.52
     insistence
    0.52
     stenosis
    0.52
     catheters
    0.52
     breasts
    0.51
    вершена
    0.51
    ᠣ
    0.50
     morate
    0.50
    Activations Density 0.011%

    No Known Activations