© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12632
    Prev
    Next
    INDEX
    Explanations

    stable main branch

    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_13_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
     М
    0.45
    好
    0.44
    設立
    0.43
    begin
    0.43
    mathrm
    0.42
     Barrio
    0.41
    М
    0.41
    ร่วม
    0.40
     माननीय
    0.40
     Д
    0.39
    POSITIVE LOGITS
     élevée
    0.50
     குறி
    0.48
     перемен
    0.47
    អំ
    0.46
    ambiente
    0.46
    unut
    0.46
    ]?
    0.46
     }"
    0.45
    idades
    0.45
    Cause
    0.43
    Activations Density 0.025%

    No Known Activations