© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173442
    Prev
    Next
    INDEX
    Explanations

    balanced perspective

    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
    ji
    0.30
    står
    0.30
    ima
    0.29
    >"
    0.28
    рят
    0.28
    нії
    0.27
    ch
    0.27
     professional
    0.27
    mi
    0.26
    iti
    0.26
    POSITIVE LOGITS
     ато
    0.29
    ⠿
    0.29
     සෑම
    0.27
     unsigned
    0.27
     millones
    0.27
     hooking
    0.27
     ஏதாவது
    0.27
     hooks
    0.26
     ен
    0.26
     अधिका
    0.26
    Activations Density 0.007%

    No Known Activations