© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210236
    Prev
    Next
    INDEX
    Explanations

    underbelly

    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_5_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
    ق
    1.60
    v
    1.59
    m
    1.55
    ם
    1.52
    da
    1.48
    de
    1.41
    ン
    1.39
    na
    1.37
    st
    1.32
    c
    1.30
    POSITIVE LOGITS
     рассказа
    1.04
    '
    1.02
    ında
    1.00
     \
    0.96
    {(\
    0.95
    fty
    0.93
    𝐡
    0.87
    الى
    0.87
    あれば
    0.87
    𝐠
    0.85
    Activations Density 0.000%

    No Known Activations