© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197476
    Prev
    Next
    INDEX
    Explanations

    code punctuation and delimiters

    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_27_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
    ɒ
    0.37
    納期
    0.35
    obr
    0.35
     மனைவி
    0.35
    ;\
    0.34
     ক্রেডিট
    0.33
    DialogFragment
    0.33
    elevation
    0.33
     कोटा
    0.33
     ambiguities
    0.33
    POSITIVE LOGITS
    惭
    0.37
    ophys
    0.37
     takes
    0.36
     사람들
    0.35
     provides
    0.35
     USAID
    0.35
     प्रतिनिध
    0.34
    takes
    0.34
     unofficial
    0.34
     informs
    0.34
    Activations Density 0.000%

    No Known Activations