© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178825
    Prev
    Next
    INDEX
    Explanations

    internal technical terms and punctuation

    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_29_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
     मनो
    0.38
     భా
    0.37
     oscillator
    0.37
     Wave
    0.36
     രൂപ
    0.35
    畈
    0.35
    佺
    0.35
     Circle
    0.34
     রাখবেন
    0.34
     ли
    0.33
    POSITIVE LOGITS
    Consume
    0.38
    NewLine
    0.37
     표
    0.37
    Frederick
    0.37
    columns
    0.36
    惑
    0.36
    punctuation
    0.36
    ിക്കേണ്ട
    0.35
    dict
    0.35
    )}},
    0.35
    Activations Density 0.037%

    No Known Activations