© 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. 143062
    Prev
    Next
    INDEX
    Explanations

    deme de anor fragment aning

    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
    是
    1.66
    {
    1.65
    你
    1.63
    _
    1.56
    し
    1.50
    。
    1.44
     powied
    1.43
    ה
    1.43
    는
    1.41
    N
    1.38
    POSITIVE LOGITS
    d
    2.05
    t
    1.91
    iz
    1.62
    dens
    1.52
    ds
    1.49
    dar
    1.46
    dalam
    1.45
    dh
    1.43
    dw
    1.39
    st
    1.38
    Activations Density 0.000%

    No Known Activations