© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171991
    Prev
    Next
    INDEX
    Explanations

    don't even think about

    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_20_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
     हॉस्पिटल
    0.45
     exclaimed
    0.44
     grinned
    0.41
     Mr
    0.41
     @"
    0.40
    PERTIES
    0.40
     billowing
    0.40
     পত্রিকার
    0.39
    のですが
    0.39
     अस्त
    0.39
    POSITIVE LOGITS
    мати
    0.46
    handleChange
    0.45
    і
    0.41
    synt
    0.41
    мі
    0.41
    лі
    0.40
    Fract
    0.40
    Autom
    0.39
    Công
    0.39
    ⃝
    0.39
    Activations Density 0.005%

    No Known Activations