© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34792
    Prev
    Next
    INDEX
    Explanations

    legal age and compliance

    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_3_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
    ווי
    0.76
    ků
    0.72
    Ꮦ
    0.70
    이가
    0.65
    URANCE
    0.65
    ﺘ
    0.64
    깥
    0.63
    
    0.63
     matériaux
    0.63
    ו
    0.62
    POSITIVE LOGITS
    c
    0.91
    b
    0.84
    et
    0.73
    st
    0.73
    ized
    0.71
    als
    0.71
    ado
    0.71
    ang
    0.70
    pass
    0.69
    pet
    0.68
    Activations Density 0.006%

    No Known Activations