© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9110
    Prev
    Next
    INDEX
    Explanations

    documentary reality shows

    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_13_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
    RELATIVA
    0.50
    нул
    0.48
    ম্ত
    0.47
     सुपारी
    0.45
    Ừ
    0.45
     demais
    0.44
    Há
    0.44
     novamente
    0.43
    ות
    0.43
    ژه
    0.43
    POSITIVE LOGITS
     d
    0.45
     t
    0.44
     adventures
    0.44
     Kardashians
    0.43
     নায়
    0.39
     T
    0.39
     D
    0.38
    v
    0.38
    c
    0.38
    kne
    0.38
    Activations Density 0.027%

    No Known Activations