© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59572
    Prev
    Next
    INDEX
    Explanations

    spouse

    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
    in
    1.77
    is
    1.52
    ir
    1.20
    是
    1.13
    는
    1.09
    ర్
    0.95
    "
    0.93
    0.91
    re
    0.91
    ut
    0.90
    POSITIVE LOGITS
    S
    1.05
    み
    1.04
    <unused642>
    1.04
    ların
    1.02
    ले
    1.01
    ㉖
    1.00
    <unused511>
    0.99
    llium
    0.98
    <unused2099>
    0.98
    ляется
    0.97
    Activations Density 0.000%

    No Known Activations