© 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. 134926
    Prev
    Next
    INDEX
    Explanations

    patisserie, rotisserie or plastics

    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
    的
    1.30
    u
    1.18
    \
    1.16
    й
    1.14
    ور
    1.02
     و
    1.02
    as
    1.01
    ू
    1.00
    好
    0.99
    ي
    0.98
    POSITIVE LOGITS
     with
    1.21
    ate
    1.13
     cramped
    1.13
     about
    1.09
    ದ
    1.09
     on
    1.08
     that
    1.08
     around
    1.04
     regarding
    0.98
    持つ
    0.98
    Activations Density 0.000%

    No Known Activations