© 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. 208742
    Prev
    Next
    INDEX
    Explanations

    all or none

    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
     largely
    0.25
    奋
    0.24
     പറയുന്നത്
    0.24
     ALI
    0.24
    嗉
    0.24
     uncanny
    0.24
     estou
    0.23
    여기
    0.23
    鳎
    0.23
     motivates
    0.23
    POSITIVE LOGITS
    icrobial
    0.29
    jší
    0.28
     Microscope
    0.28
    zkod
    0.28
     microbe
    0.26
     हाइड्रो
    0.26
     Microbial
    0.25
     выбор
    0.24
    hapsody
    0.24
    wa
    0.24
    Activations Density 0.001%

    No Known Activations