© 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. 257092
    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
    و
    1.24
    ep
    1.15
    ter
    1.10
    ीकरण
    1.03
    к
    0.99
    ounce
    0.97
    tt
    0.97
     fim
    0.97
     щоб
    0.96
    quirer
    0.95
    POSITIVE LOGITS
     unul
    1.18
    Portug
    1.15
     reden
    1.14
    لاً
    1.13
    ربعة
    1.12
     één
    1.11
    ச
    1.10
     bookArray
    1.09
     learns
    1.09
     Estadística
    1.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.