© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229318
    Prev
    Next
    INDEX
    Explanations

    say "2"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ishly
    0.38
    brows
    0.37
    Lo
    0.36
    ಅ
    0.36
    意
    0.35
    alliance
    0.35
    ierende
    0.35
    สำ
    0.35
    DON
    0.34
     "????
    0.34
    POSITIVE LOGITS
    ,+\
    0.40
     arquivos
    0.38
    鸮
    0.38
     sensibilidad
    0.38
     किरण
    0.38
    oyu
    0.37
     penta
    0.37
    ंदा
    0.37
     sphing
    0.37
     ht
    0.36
    Activations Density 0.001%

    No Known Activations