© 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. 173053
    Prev
    Next
    INDEX
    Explanations

    create directory

    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
     způ
    0.43
     dapibus
    0.42
    ស
    0.42
     pointe
    0.41
    парт
    0.40
     भागीदारों
    0.40
     trabajó
    0.40
    ága
    0.39
    excitation
    0.39
    ज्
    0.38
    POSITIVE LOGITS
     Gera
    0.48
     Lumber
    0.47
     Stockholm
    0.46
     Помимо
    0.45
     G
    0.44
     Entrada
    0.42
     Proses
    0.42
    ക്കിയ
    0.41
     General
    0.41
     контро
    0.41
    Activations Density 0.001%

    No Known Activations