© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37320
    Prev
    Next
    INDEX
    Explanations

    cabana, sabana, banana

    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
    ara
    0.89
    ر
    0.84
    an
    0.82
    a
    0.81
    yl
    0.80
    z
    0.77
    ak
    0.73
    ه
    0.73
    af
    0.73
    val
    0.73
    POSITIVE LOGITS
     unrecognizable
    0.78
     furtherance
    0.75
    یل
    0.73
    ری
    0.72
     tablero
    0.71
     undulating
    0.70
     maximising
    0.70
    ўся
    0.68
    왜
    0.67
    える
    0.66
    Activations Density 0.000%

    No Known Activations