© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59603
    Prev
    Next
    INDEX
    Explanations

    never or every

    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_2_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
     it
    1.52
     ότι
    1.34
    ری
    1.30
    いた
    1.23
    ف
    1.23
    os
    1.23
    ุ
    1.20
    ش
    1.19
    ك
    1.18
    ا
    1.17
    POSITIVE LOGITS
    -
    1.36
    ០
    1.03
    ᆺ
    1.01
    ר
    0.93
     frustrated
    0.92
     disgruntled
    0.92
    ৫
    0.91
    ޟ
    0.91
     K
    0.88
     deflection
    0.88
    Activations Density 0.003%

    No Known Activations