© 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. 75342
    Prev
    Next
    INDEX
    Explanations

    the end, the same, the whole

    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
     Espresso
    0.35
     într
    0.34
     espresso
    0.33
    Esp
    0.32
    ଈ
    0.32
    ពេ
    0.32
     треуго
    0.32
    テンプレート
    0.32
     improper
    0.31
    hôtel
    0.31
    POSITIVE LOGITS
     ይታ
    0.37
     наре
    0.36
     ولي
    0.35
    ]]:
    0.34
    특별
    0.34
    ன்களை
    0.33
     ordin
    0.33
     शहरी
    0.33
    щении
    0.32
    DataAccess
    0.32
    Activations Density 0.010%

    No Known Activations