© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 233717
    Prev
    Next
    INDEX
    Explanations

    byte sequences

    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_46_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
     失
    0.46
    ニコ
    0.42
    枢
    0.41
     Utopia
    0.39
    BRAS
    0.38
    蝶
    0.38
    หล
    0.38
     ধাতু
    0.38
     Statistik
    0.38
    失
    0.38
    POSITIVE LOGITS
    ༣
    0.41
     obstructed
    0.40
     glued
    0.38
     Kathy
    0.38
     आईएफ
    0.38
    Kathy
    0.37
     Resin
    0.36
     pave
    0.36
     seventeenth
    0.36
     bày
    0.36
    Activations Density 0.002%

    No Known Activations