© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90913
    Prev
    Next
    INDEX
    Explanations

    "new hope"

    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_3_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
    1.01
    0
    0.88
     in
    0.88
    ية
    0.83
    ut
    0.77
    ></
    0.71
    able
    0.66
    ard
    0.66
    ul
    0.65
    ih
    0.65
    POSITIVE LOGITS
    。
    0.80
    لای
    0.74
    dirs
    0.70
    جیت
    0.70
    لڈ
    0.66
    لین
    0.65
    ।
    0.65
    setKeepCallback
    0.63
    אנ
    0.63
    لە
    0.62
    Activations Density 0.005%

    No Known Activations