© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202436
    Prev
    Next
    INDEX
    Explanations

    names of places and people

    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_37_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
    ियां
    0.37
    HING
    0.35
    odb
    0.35
     بنیاد
    0.35
    ઙ
    0.35
    Texto
    0.34
    ходу
    0.34
    次は
    0.33
    шкой
    0.33
    붕
    0.33
    POSITIVE LOGITS
    者の
    0.46
     milik
    0.44
    她的
    0.42
    $.\
    0.41
    ibli
    0.40
    자의
    0.40
    者的
    0.40
     hers
    0.40
     미국의
    0.37
     السيد
    0.37
    Activations Density 0.055%

    No Known Activations