© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143638
    Prev
    Next
    INDEX
    Explanations

    kw followed by word endings

    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
    -
    1.69
    ي
    1.63
    ير
    1.59
    ر
    1.55
    н
    1.53
     sûr
    1.52
    ν
    1.43
    νες
    1.41
    νε
    1.39
     produz
    1.38
    POSITIVE LOGITS
    l
    1.80
    d
    1.72
    s
    1.66
    v
    1.66
    den
    1.63
    dance
    1.62
    g
    1.61
    st
    1.59
    dalam
    1.55
    m
    1.54
    Activations Density 0.000%

    No Known Activations