© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217385
    Prev
    Next
    INDEX
    Explanations

    breaking something, physically or metaphorically

    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_16_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
    
    0.50
     교회
    0.50
    ⏪
    0.49
    INUS
    0.49
    rewsbury
    0.48
    ⛪
    0.48
     Gewalt
    0.47
     القر
    0.47
     ومع
    0.47
     කිරීමට
    0.46
    POSITIVE LOGITS
    a
    0.66
     on
    0.65
    d
    0.61
    e
    0.57
    on
    0.54
    o
    0.54
    town
    0.53
    i
    0.52
    n
    0.52
    in
    0.50
    Activations Density 0.000%

    No Known Activations