© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130509
    Prev
    Next
    INDEX
    Explanations

    transmit, transponder

    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_1_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
    ي
    2.08
    ра
    1.66
    ка
    1.65
    ن
    1.65
    ق
    1.59
    ك
    1.55
    س
    1.52
    ت
    1.49
    י
    1.45
    ur
    1.45
    POSITIVE LOGITS
    I
    1.00
     It
    0.90
     was
    0.88
     unspoken
    0.86
    :
    0.85
     yang
    0.83
     X
    0.83
    U
    0.81
    ))
    0.81
    ']
    0.80
    Activations Density 0.001%

    No Known Activations