© 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. 90697
    Prev
    Next
    INDEX
    Explanations

    designed for/to

    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
     ส
    0.79
    ่
    0.76
     '
    0.75
     I
    0.74
     ی
    0.72
     outlay
    0.69
     agreg
    0.69
     abortions
    0.69
     ofer
    0.68
     arcs
    0.67
    POSITIVE LOGITS
    {
    1.22
    on
    1.08
    ري
    0.95
    ната
    0.80
    اك
    0.80
    ли
    0.74
    ackBar
    0.73
    {//
    0.73
    ו
    0.71
    存在
    0.71
    Activations Density 0.010%

    No Known Activations