© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59344
    Prev
    Next
    INDEX
    Explanations

    unexpected X

    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_2_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
     ότι
    1.38
    いた
    1.33
    ков
    1.31
    ре
    1.28
    ро
    1.25
    س
    1.19
    ник
    1.18
    あ
    1.18
    活用
    1.13
    quela
    1.13
    POSITIVE LOGITS
    is
    2.02
    ר
    1.95
    n
    1.65
    in
    1.33
     L
    1.32
    i
    1.30
    ᆺ
    1.30
    el
    1.27
    for
    1.25
    ۰
    1.24
    Activations Density 0.005%

    No Known Activations