© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46032
    Prev
    Next
    INDEX
    Explanations

    addressing the audience

    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_22_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
    nicheskij
    0.46
    menu
    0.44
     classifiers
    0.44
    ウェイ
    0.44
     निकालकर
    0.42
     मंत्रिपरिषद
    0.42
    莯
    0.40
    WAY
    0.40
    主的
    0.40
     medalist
    0.39
    POSITIVE LOGITS
     Gewinn
    0.41
    accum
    0.40
     Gb
    0.39
    ো
    0.37
     dew
    0.37
     dovuto
    0.36
     athleticism
    0.36
     comenzar
    0.36
    тере
    0.35
     Rv
    0.35
    Activations Density 0.000%

    No Known Activations