© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197539
    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_26_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
     phosphorylation
    0.50
     depreciation
    0.48
     research
    0.45
     expenditures
    0.45
     internalization
    0.44
    \},\
    0.44
     depletion
    0.44
     preaching
    0.44
     დიდი
    0.44
     tangy
    0.42
    POSITIVE LOGITS
    通道
    0.47
    暠
    0.45
    CAT
    0.44
    सर्
    0.43
     социально
    0.43
     MTL
    0.42
     στους
    0.42
    습니다
    0.42
    初
    0.42
    rah
    0.41
    Activations Density 0.000%

    No Known Activations