© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131814
    Prev
    Next
    INDEX
    Explanations

    comeback player

    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_1_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
    ون
    1.51
    는
    1.16
    ۔
    1.12
    2
    1.06
    اي
    1.02
    ۲
    1.01
    ні
    0.99
    ↵
    0.97
    _',
    0.94
    ляется
    0.93
    POSITIVE LOGITS
     for
    1.30
     (
    1.25
    t
    1.08
     as
    1.04
    0.97
     be
    0.96
     ouv
    0.93
    し
    0.90
    était
    0.85
    r
    0.83
    Activations Density 0.000%

    No Known Activations