© 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. 256581
    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
    goers
    1.41
    apartment
    1.41
    ेन
    1.39
    ㅉ
    1.36
    yı
    1.32
    ejb
    1.29
    م
    1.29
    ೇವಿನ
    1.28
    grained
    1.28
    expensive
    1.28
    POSITIVE LOGITS
     beh
    1.03
    ภาพ
    1.01
     proper
    0.97
    न्ध
    0.95
    न्न
    0.95
    ssss
    0.95
    sau
    0.94
    ૦
    0.93
     drain
    0.91
     pengh
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.