© 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. 83332
    Prev
    Next
    INDEX
    Explanations

    spectrum

    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
     in
    1.84
    在
    1.84
    y
    1.28
    會
    1.20
    ње
    1.16
     In
    1.16
     a
    1.09
    的
    1.09
    స
    1.08
    在意
    1.07
    POSITIVE LOGITS
    for
    2.00
     for
    1.36
    ри
    1.34
    meler
    1.32
    if
    1.30
    ।
    1.22
    ת
    1.22
    mills
    1.21
    {
    1.20
    oe
    1.20
    Activations Density 0.001%

    No Known Activations