© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157390
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Pontiac
    0.42
     Widers
    0.40
    അ
    0.39
     ಪಡೆಯ
    0.39
    Gam
    0.38
    reserved
    0.37
    Converted
    0.36
     آنا
    0.36
    Riv
    0.36
     Advanced
    0.36
    POSITIVE LOGITS
    𝘞
    0.41
     xr
    0.38
    ipers
    0.38
    πη
    0.38
     sash
    0.38
    oping
    0.37
    sas
    0.36
    перы
    0.35
     Sas
    0.35
    っくり
    0.35
    Activations Density 0.000%

    No Known Activations