© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32109
    Prev
    Next
    INDEX
    Explanations

    Monterey Bay Aquarium

    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_7_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
    á
    0.85
    id
    0.85
     N
    0.79
     Pilih
    0.73
     K
    0.73
     Çok
    0.73
    ㅋㅋ
    0.73
     Labrenzia
    0.73
    S
    0.72
    au
    0.71
    POSITIVE LOGITS
    '
    0.75
    ING
    0.71
    ت
    0.63
    ing
    0.62
    ↵↵↵
    0.62
    ↵↵↵↵↵
    0.56
    จะ
    0.56
    ة
    0.53
    ↵↵↵↵
    0.52
     الولايات
    0.51
    Activations Density 0.001%

    No Known Activations