© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172535
    Prev
    Next
    INDEX
    Explanations

    int parameter declarations

    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_20_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
    ционным
    0.43
    ционный
    0.42
    рна
    0.42
     derivados
    0.41
    矢量
    0.40
     যুক্তি
    0.39
    ционных
    0.39
     て
    0.39
    linhas
    0.39
     torsion
    0.38
    POSITIVE LOGITS
    it
    0.45
    Hollywood
    0.41
     päiv
    0.40
    反而
    0.40
    uts
    0.39
     ilg
    0.38
    DW
    0.38
    ŠE
    0.38
    İ
    0.38
    Ħ
    0.37
    Activations Density 0.001%

    No Known Activations