© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259027
    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
     넣어
    1.30
    asă
    1.25
     फेब्रुवारी
    1.22
     불러
    1.20
     pâle
    1.17
     思っ
    1.17
     양
    1.16
    ྥ
    1.14
    요
    1.14
     EBS
    1.14
    POSITIVE LOGITS
     realidade
    1.16
    chips
    1.11
     allies
    1.10
     ascend
    1.10
     Lampard
    1.06
     tangents
    1.04
     rivals
    1.03
     golpes
    1.02
     bosses
    1.01
     scour
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.