© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218098
    Prev
    Next
    INDEX
    Explanations

    php in URLs

    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_31_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
    															
    0.38
     bath
    0.38
     founded
    0.38
     bony
    0.38
    Accommodation
    0.37
    Duration
    0.36
     accommodation
    0.36
    Renew
    0.36
     근
    0.35
    イヤー
    0.35
    POSITIVE LOGITS
     frame
    0.39
     Journalism
    0.39
     flurry
    0.38
    <0x1D>
    0.37
    frame
    0.36
     fase
    0.36
     மிகப்பெ
    0.36
     Eulerian
    0.36
    ালেন
    0.36
     Tree
    0.35
    Activations Density 0.000%

    No Known Activations