© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46740
    Prev
    Next
    INDEX
    Explanations

    YY followed by airport codes or dates

    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_10_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
    </h2>
    0.85
    </h3>
    0.82
    t
    0.76
    ма
    0.72
    1
    0.71
    we
    0.66
    n
    0.64
    </b>
    0.61
    dash
    0.61
    marble
    0.61
    POSITIVE LOGITS
    anians
    0.67
     interno
    0.64
     refunds
    0.63
     intu
    0.62
     ably
    0.62
     Observatory
    0.61
    खुद
    0.61
     rosters
    0.60
    もちろん
    0.60
     arrays
    0.59
    Activations Density 0.004%

    No Known Activations