© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81691
    Prev
    Next
    INDEX
    Explanations

    second

    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_0_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
    ي
    1.77
     a
    1.66
    י
    1.65
    ק
    1.60
    ி
    1.59
    न
    1.44
    א
    1.38
    лся
    1.31
    ン
    1.24
    น
    1.23
    POSITIVE LOGITS
    y
    1.50
    the
    1.43
    AL
    1.38
    >
    1.33
    t
    1.31
    g
    1.30
    ो
    1.29
    ing
    1.25
    s
    1.22
    ot
    1.18
    Activations Density 0.001%

    No Known Activations