© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152686
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
      
    0.57
     ล
    0.48
     ท
    0.45
     t
    0.45
     พ
    0.45
     tamb
    0.44
     나타
    0.44
     ใน
    0.43
     ທ
    0.43
     제
    0.43
    POSITIVE LOGITS
    *
    2.06
    *,
    1.46
    *\
    1.34
    *',
    1.34
    *",
    1.31
    ()*
    1.30
    *;
    1.29
    *$
    1.28
    *.
    1.27
    ,*
    1.26
    Activations Density 0.057%

    No Known Activations