© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257590
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    ೋಗ್ಯ
    1.20
    ون
    1.20
    ely
    1.17
    %>%
    1.16
    arily
    1.16
    ene
    1.15
    Sumber
    1.14
    疮
    1.12
     ràng
    1.12
     graciously
    1.11
    POSITIVE LOGITS
    ால்
    1.25
     legato
    1.20
    的问题
    1.15
    agine
    1.10
    يط
    1.09
     aggressive
    1.08
    ു
    1.07
    мом
    1.07
    циям
    1.06
    ИА
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.