© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7401
    Prev
    Next
    INDEX
    Explanations

    agreement

    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_40_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
    厉害
    0.38
    Gruß
    0.36
    デッキ
    0.35
    lords
    0.35
    噸
    0.35
    bil
    0.34
    Caractéristiques
    0.34
    toLocale
    0.34
    registry
    0.33
    主力
    0.33
    POSITIVE LOGITS
     well
    0.73
     Well
    0.70
    Well
    0.68
     WELL
    0.64
    well
    0.56
    WELL
    0.50
     добре
    0.49
     잘
    0.47
     dobrze
    0.46
     хорошо
    0.45
    Activations Density 0.087%

    No Known Activations