© 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. 49784
    Prev
    Next
    INDEX
    Explanations

    });});

    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
    Ownership
    0.34
     置
    0.33
    SwingConstants
    0.32
    AndroidManifest
    0.32
     portée
    0.31
     پشت
    0.31
    즈
    0.31
    立て
    0.30
     собственности
    0.30
     govori
    0.30
    POSITIVE LOGITS
    crc
    0.30
     last
    0.29
     deepest
    0.29
     Ram
    0.29
     seinen
    0.29
     العم
    0.29
    ec
    0.28
     cultivated
    0.28
    عم
    0.28
     tested
    0.28
    Activations Density 0.003%

    No Known Activations