© 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. 229359
    Prev
    Next
    INDEX
    Explanations

    N sounds

    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
    CoO
    0.45
    ссо
    0.43
    נדה
    0.40
    شو
    0.39
    铷
    0.38
    issive
    0.38
    倪
    0.38
    PIO
    0.38
    ACO
    0.37
    DBObject
    0.37
    POSITIVE LOGITS
    נו
    1.30
    노
    0.99
    Nom
    0.98
     نو
    0.98
    ной
    0.96
    诺
    0.96
     Nom
    0.95
     но
    0.92
    نو
    0.91
    nom
    0.90
    Activations Density 0.000%

    No Known Activations