© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13007
    Prev
    Next
    INDEX
    Explanations

    ascii characters

    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_40_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
     spelt
    0.59
     spelling
    0.58
     Spelling
    0.57
     spelled
    0.55
     digits
    0.54
     syllable
    0.51
     읽
    0.51
     syllables
    0.51
     sequence
    0.50
     spell
    0.50
    POSITIVE LOGITS
     MIC
    0.37
     Textile
    0.36
    getFocusAreas
    0.36
     genetic
    0.36
     briefing
    0.36
     Bicycle
    0.36
     lingerie
    0.36
    즙
    0.36
     wet
    0.36
     Genetic
    0.36
    Activations Density 0.105%

    No Known Activations