© 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. 60161
    Prev
    Next
    INDEX
    Explanations

    at times

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     chis
    0.57
     chum
    0.56
    茣
    0.55
     session
    0.55
     dépend
    0.55
     conventionally
    0.55
     pravidel
    0.54
     amit
    0.53
     tedes
    0.52
    àm
    0.52
    POSITIVE LOGITS
    Invalids
    0.63
     Heterocycl
    0.62
     ハ
    0.58
    பிர
    0.57
     அவர்கள்
    0.56
    র্ব
    0.55
     여성
    0.55
     Methodology
    0.54
     ホ
    0.54
    われている
    0.53
    Activations Density 0.001%

    No Known Activations