© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203782
    Prev
    Next
    INDEX
    Explanations

    operating systems or OSes followed by punctuation or details

    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_6_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
    h
    0.68
    <0xAC>
    0.67
    א
    0.63
    1
    0.60
    ти
    0.58
    들이
    0.57
    lar
    0.57
    <0x80>
    0.56
    ین
    0.55
    ores
    0.54
    POSITIVE LOGITS
     to
    0.65
     toată
    0.61
     atualizar
    0.59
    વું
    0.58
    čina
    0.57
     Qualquer
    0.56
     be
    0.56
    的方式
    0.55
     digraph
    0.55
     fuc
    0.54
    Activations Density 0.000%

    No Known Activations