© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33943
    Prev
    Next
    INDEX
    Explanations

    setting Impact

    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
    0.91
    0.83
    0.80
    z
    0.71
    0.70
    \
    0.69
    é
    0.68
    j
    0.67
    one
    0.64
     \
    0.64
    POSITIVE LOGITS
    ラの
    0.89
    های
    0.88
    ađ
    0.79
    ນ
    0.78
    した
    0.77
    ریک
    0.77
    치
    0.76
    માં
    0.73
    กว่า
    0.70
    ر
    0.70
    Activations Density 0.011%

    No Known Activations