© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165423
    Prev
    Next
    INDEX
    Explanations

    roller skates and derby

    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
     corrente
    0.54
     kişi
    0.50
    i
    0.49
    eni
    0.49
     Сен
    0.49
     ploch
    0.48
    ef
    0.48
    election
    0.47
    etest
    0.47
    n
    0.47
    POSITIVE LOGITS
    ابر
    0.49
     Expires
    0.48
    ස්
    0.46
    गरण
    0.44
    בת
    0.44
    раи
    0.44
     Oral
    0.43
    Ler
    0.42
    arynx
    0.42
    াইয়৷
    0.42
    Activations Density 0.001%

    No Known Activations