© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89562
    Prev
    Next
    INDEX
    Explanations

    Sudan, South Sudan, nationalities, Brazil, Minas Gerais

    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_3_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
    то
    0.77
    dehyde
    0.66
    дцать
    0.66
    )$
    0.63
    ности
    0.63
    を受ける
    0.61
    ０
    0.60
    )،
    0.59
     searches
    0.58
    られた
    0.58
    POSITIVE LOGITS
    al
    0.81
     I
    0.76
    ing
    0.75
    S
    0.74
    et
    0.72
    y
    0.71
    ని
    0.70
    U
    0.69
    v
    0.68
    as
    0.67
    Activations Density 0.001%

    No Known Activations