© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51772
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific item counts

    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_30_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
     diverg
    0.39
    𝗮
    0.39
     BOTH
    0.38
     {//
    0.37
    ){//
    0.36
    㳒
    0.35
     autop
    0.35
     disappearing
    0.34
    ﻅ
    0.34
     paramagnetic
    0.34
    POSITIVE LOGITS
    CCE
    0.40
    柰
    0.39
    sized
    0.38
    rela
    0.37
     sized
    0.33
    고요
    0.33
    UEN
    0.33
    cous
    0.33
    iliency
    0.32
    partition
    0.32
    Activations Density 0.006%

    No Known Activations