© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 148844
    Prev
    Next
    INDEX
    Explanations

    crew socks

    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_18_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
     अपने
    0.51
    मौ
    0.50
    囵
    0.48
     όχι
    0.47
    ప
    0.46
     unconsciously
    0.46
    胫
    0.46
    ืด
    0.45
     实
    0.45
    લી
    0.45
    POSITIVE LOGITS
     (
    0.52
     posing
    0.48
     microphones
    0.47
    =
    0.46
    iyoruz
    0.46
    izations
    0.45
     коль
    0.45
     yaz
    0.44
    ners
    0.44
     preparatory
    0.44
    Activations Density 0.000%

    No Known Activations