© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59862
    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_11_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
    </h3>
    0.48
    </h1>
    0.44
     estoppel
    0.44
    </h2>
    0.44
    :::
    0.43
     causation
    0.43
     refocus
    0.43
    )))
    0.43
     cholinergic
    0.43
     nonzero
    0.42
    POSITIVE LOGITS
    ized
    0.50
    炰
    0.48
    炲
    0.46
     化
    0.45
     mici
    0.44
     Ellos
    0.44
     persondata
    0.43
    am
    0.43
     wacht
    0.43
    ায়
    0.43
    Activations Density 0.000%

    No Known Activations