© 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. 197673
    Prev
    Next
    INDEX
    Explanations

    1

    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
     अड
    0.38
    Thr
    0.38
     échantillons
    0.38
     Stry
    0.37
     Axes
    0.37
     **)
    0.37
    orical
    0.37
    BeforeCall
    0.36
    "--
    0.36
     ব্রাজ
    0.36
    POSITIVE LOGITS
     Bailey
    0.56
    Bailey
    0.53
     nine
    0.46
    Ба
    0.45
     RAN
    0.44
     BAI
    0.42
    bau
    0.42
    ချ
    0.41
    bai
    0.41
    aban
    0.41
    Activations Density 0.006%

    No Known Activations