© 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. 35104
    Prev
    Next
    INDEX
    Explanations

    glass shape, hour angle, hours worked

    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
    i
    0.75
    t
    0.73
    an
    0.66
    
    0.65
     eup
    0.64
    すごく
    0.63
    iiv
    0.61
     comenc
    0.60
    Ɛ
    0.60
    rectangle
    0.59
    POSITIVE LOGITS
    ص
    1.15
    ور
    0.91
    ول
    0.89
    ل
    0.89
    ج
    0.86
    ુ
    0.82
     for
    0.79
    綪
    0.76
    ру
    0.75
    ल
    0.75
    Activations Density 0.000%

    No Known Activations