© 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. 257501
    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
     snippet
    1.34
    takes
    1.32
    it
    1.29
    speak
    1.21
    take
    1.20
    𝘵
    1.18
    sit
    1.15
     खर्चा
    1.15
    ச
    1.14
     excuse
    1.13
    POSITIVE LOGITS
    RestorePolicy
    1.22
     restable
    1.15
     Vanilla
    1.11
     والاست
    1.10
    
    1.09
     cál
    1.07
    đi
    1.06
    ienst
    1.05
     Burial
    1.05
     στους
    1.03
    Activations Density 0.000%

    No Known Activations