© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170898
    Prev
    Next
    INDEX
    Explanations

    book metadata tags

    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
    فل
    0.48
     行っ
    0.42
    Repe
    0.42
    ﺎ
    0.41
    )):
    0.40
    ДЕ
    0.40
    ').
    0.39
     Кири
    0.39
    мом
    0.39
    FU
    0.38
    POSITIVE LOGITS
    ú
    0.48
     Book
    0.47
    é
    0.47
    šia
    0.47
    dört
    0.47
    is
    0.46
    oinen
    0.46
    unächst
    0.46
    ár
    0.45
     four
    0.45
    Activations Density 0.000%

    No Known Activations