© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209185
    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_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
     blistering
    0.52
    ಂಗ್
    0.50
    𝗹
    0.49
    goal
    0.47
     فی
    0.45
     좋
    0.44
    付ける
    0.44
     امید
    0.44
     heaped
    0.44
    तरंज
    0.44
    POSITIVE LOGITS
     Root
    0.53
    ATH
    0.52
    Root
    0.47
     Nodes
    0.46
     Colon
    0.46
    AD
    0.46
     Plant
    0.45
    ]-
    0.45
    DF
    0.44
     tsh
    0.44
    Activations Density 0.000%

    No Known Activations