© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43856
    Prev
    Next
    INDEX
    Explanations

    Gemma

    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_22_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
    to
    0.48
    ated
    0.47
    i
    0.47
     creep
    0.46
     to
    0.45
     soon
    0.45
     was
    0.44
    ία
    0.44
     bond
    0.44
    \
    0.44
    POSITIVE LOGITS
    ഗ്ര
    0.54
    Baptiste
    0.53
     증
    0.48
     റെ
    0.48
    에서의
    0.48
    Aux
    0.48
     경로
    0.48
    ุปกรณ์
    0.48
     लोकार्
    0.47
    operateur
    0.47
    Activations Density 0.000%

    No Known Activations