© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194197
    Prev
    Next
    INDEX
    Explanations

    Eurasia / Eurasian

    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_4_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
    ?
    1.09
    !
    1.04
    on
    1.02
    at
    0.98
     on
    0.83
     one
    0.82
     $
    0.80
     the
    0.79
     an
    0.78
    ong
    0.76
    POSITIVE LOGITS
    もら
    0.84
     composés
    0.78
     effectués
    0.78
     carénés
    0.77
     устройств
    0.74
     médiocrement
    0.73
    𝐼
    0.73
     gắng
    0.70
     válv
    0.69
     вулкан
    0.69
    Activations Density 0.003%

    No Known Activations