© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49721
    Prev
    Next
    INDEX
    Explanations

    specific details or memories

    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
     Offered
    0.31
     thousands
    0.30
    regulars
    0.30
     افغانستان
    0.30
    圴
    0.30
    Charlotte
    0.30
     যুক্তরাষ্ট্র
    0.29
     geslacht
    0.29
     Splash
    0.29
     उन्ह
    0.29
    POSITIVE LOGITS
    untamiento
    0.34
    яў
    0.32
    ۜ
    0.31
    Quality
    0.30
    yfik
    0.30
    評価
    0.30
    痹
    0.30
     Grassmann
    0.30
    品質
    0.29
     розви
    0.29
    Activations Density 0.014%

    No Known Activations