© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130586
    Prev
    Next
    INDEX
    Explanations

    cellar / formula / infect

    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_1_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
    2
    1.40
     by
    1.23
    0
    1.18
    by
    1.05
    ش
    0.98
     \
    0.95
    piration
    0.95
    ma
    0.90
     and
    0.89
    ال
    0.89
    POSITIVE LOGITS
    る
    1.13
    ด้าน
    1.09
    ти
    1.06
    تر
    1.02
     tierras
    1.02
    ा
    1.02
    쓰
    1.01
     clínicas
    1.00
     rápid
    0.99
     gráf
    0.98
    Activations Density 0.000%

    No Known Activations