© 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. 130335
    Prev
    Next
    INDEX
    Explanations

    bratwurst or burger

    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
     in
    1.45
    ON
    1.42
    在
    1.40
    ER
    1.30
    0
    1.29
    Y
    1.27
    AL
    1.16
    的
    1.16
    ام
    1.15
    IN
    1.12
    POSITIVE LOGITS
    т
    1.42
    ва
    1.15
    τι
    1.07
     Вя
    1.06
     Испа
    1.02
     anciennes
    1.00
    йо
    0.99
    ances
    0.97
     Пас
    0.97
     Администра
    0.96
    Activations Density 0.000%

    No Known Activations