© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231933
    Prev
    Next
    INDEX
    Explanations

    data handling

    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_6_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
     for
    0.89
    ных
    0.87
    ى
    0.72
    ного
    0.68
    с
    0.68
    ные
    0.68
    ро
    0.66
    ALL
    0.66
    OME
    0.66
    ORA
    0.66
    POSITIVE LOGITS
    த்தில்
    1.02
    ط
    0.95
    આ
    0.82
    क्षिप्त
    0.80
    يل
    0.79
     hanno
    0.78
     lleg
    0.77
    posição
    0.75
    and
    0.74
    ulare
    0.73
    Activations Density 0.002%

    No Known Activations