© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209188
    Prev
    Next
    INDEX
    Explanations

    text or non-english words

    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_20_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
    HV
    0.38
    UES
    0.33
    NGO
    0.32
     contributors
    0.31
     спла
    0.30
     --
    0.30
    OKR
    0.29
    人数
    0.29
     иных
    0.29
    по
    0.29
    POSITIVE LOGITS
     soleil
    0.42
     Από
    0.38
    ቹን
    0.36
     सड़क
    0.36
    ਾਨੂੰ
    0.36
     $:
    0.35
    renaline
    0.35
     জ্বল
    0.35
     ਜੋ
    0.35
     þat
    0.35
    Activations Density 0.035%

    No Known Activations