© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196960
    Prev
    Next
    INDEX
    Explanations

    words describing something novel, creative, or unconventional.

    oai_token-act-pair · claude-4-5-haikuTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     Feminist
    0.53
    મ્
    0.46
     feminist
    0.46
     Dany
    0.44
    義
    0.44
    صح
    0.44
    쥴
    0.44
     Whistler
    0.43
     disregard
    0.43
    ardom
    0.43
    POSITIVE LOGITS
    Insets
    0.55
    ارتی
    0.46
     bolsillo
    0.45
     #${
    0.44
    dataIn
    0.43
     لگاتا
    0.43
    Milk
    0.43
    leftharpoons
    0.43
    zinha
    0.42
     단
    0.42
    Activations Density 0.000%

    No Known Activations