© 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. 209422
    Prev
    Next
    INDEX
    Explanations

    20s version numbers

    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
    者的
    0.48
    迭代
    0.45
     infraestructura
    0.44
     cri
    0.43
    睜
    0.43
    祺
    0.43
     caratteristiche
    0.43
    㠻
    0.43
     Hangzhou
    0.43
    壩
    0.42
    POSITIVE LOGITS
    +
    0.43
    ＋
    0.42
    zyme
    0.39
    ell
    0.39
    ł
    0.39
    vý
    0.38
    ål
    0.38
    yst
    0.38
    elt
    0.37
    ymethyl
    0.37
    Activations Density 0.000%

    No Known Activations