© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201652
    Prev
    Next
    INDEX
    Explanations

    cuBLAS libraries

    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_6_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
    their
    1.17
     a
    1.15
    they
    1.13
    a
    1.09
    t
    1.08
    ar
    1.06
    there
    1.06
    i
    1.06
    f
    1.05
    rt
    1.03
    POSITIVE LOGITS
     bás
    0.91
    ít
    0.89
     autorización
    0.88
     señalado
    0.88
    스는
    0.87
     exámenes
    0.86
    కు
    0.86
     usuário
    0.85
    <0x0D>
    0.85
     eléct
    0.84
    Activations Density 0.000%

    No Known Activations