© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261352
    Prev
    Next
    INDEX
    Explanations

    Skynet and related concepts

    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_5_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
    h
    1.70
    a
    1.67
    at
    1.61
    ed
    1.34
    al
    1.33
    n
    1.30
    o
    1.30
     in
    1.24
    id
    1.24
    er
    1.22
    POSITIVE LOGITS
     спорттук
    0.95
    のエ
    0.91
    かっこ
    0.90
    Пре
    0.89
    Об
    0.88
    Дру
    0.88
     ಕನ
    0.87
    Cantidad
    0.86
     Puedes
    0.86
     Apesar
    0.86
    Activations Density 0.000%

    No Known Activations