© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158952
    Prev
    Next
    INDEX
    Explanations

    eje x, sé claro/específico

    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_2_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
    at
    0.90
    ↵
    0.76
    u
    0.71
    y
    0.67
    i
    0.66
    O
    0.65
    -
    0.64
    :
    0.64
     huvud
    0.63
    Õ
    0.62
    POSITIVE LOGITS
    ک
    1.13
    ব
    1.04
    ס
    1.03
    マ
    0.99
    ז
    0.98
    з
    0.97
    ку
    0.96
    티
    0.95
    カ
    0.94
    ла
    0.93
    Activations Density 0.000%

    No Known Activations