© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83637
    Prev
    Next
    INDEX
    Explanations

    expensive

    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
    。
    1.63
    ým
    1.40
    )。
    1.39
     be
    1.38
    će
    1.31
    ।
    1.31
    the
    1.27
    ।’
    1.24
     कपड़े
    1.17
    يت
    1.16
    POSITIVE LOGITS
    ل
    2.06
    os
    1.80
    us
    1.72
    l
    1.72
    v
    1.70
    í
    1.60
    ки
    1.56
    ik
    1.54
    т
    1.50
    ت
    1.48
    Activations Density 0.002%

    No Known Activations