© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243495
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     남
    0.38
    協力
    0.37
    ให้
    0.37
    Hung
    0.36
     sinus
    0.36
    issors
    0.36
    </bbox>
    0.35
     Safegu
    0.35
    얽
    0.35
    жами
    0.35
    POSITIVE LOGITS
     deliveries
    0.48
    ब्बत
    0.45
     delivery
    0.42
     translateX
    0.40
     uds
    0.39
    ழ்ச்ச
    0.39
    achan
    0.38
     Ärzte
    0.38
    咸
    0.38
     кан
    0.37
    Activations Density 0.000%

    No Known Activations