© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102272
    Prev
    Next
    INDEX
    Explanations

    words ending in ized or powered

    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_14_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
     ну
    0.63
    イド
    0.53
     সংখ
    0.52
     甘
    0.51
     број
    0.50
    CharCode
    0.49
     groaned
    0.49
     Idha
    0.48
    ну
    0.48
    ț
    0.48
    POSITIVE LOGITS
    इंडिया
    0.54
     wasteful
    0.52
    BA
    0.51
    urdy
    0.51
    home
    0.50
     Fot
    0.49
    <h3>
    0.49
     broader
    0.49
     मिलते
    0.48
    FIFA
    0.48
    Activations Density 0.001%

    No Known Activations