© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18249
    Prev
    Next
    INDEX
    Explanations

    eavesdropping, essentially

    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
     towers
    1.07
     tower
    0.98
     Towers
    0.98
     Tower
    0.87
    Tower
    0.87
    tower
    0.82
     turret
    0.73
    塔
    0.72
     torre
    0.71
     torres
    0.65
    POSITIVE LOGITS
     man
    0.75
     MIT
    0.66
     Mit
    0.64
     Man
    0.63
    Man
    0.62
    MIT
    0.56
    Mit
    0.52
    man
    0.51
    mit
    0.49
     MAN
    0.48
    Activations Density 0.148%

    No Known Activations