© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14720
    Prev
    Next
    INDEX
    Explanations

    New Hampshire primary

    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_13_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
    را
    0.54
    рети
    0.49
     -
    0.48
    ρου
    0.48
    raw
    0.48
     Clown
    0.47
    .',
    0.47
     достовер
    0.47
    ädig
    0.46
    loser
    0.46
    POSITIVE LOGITS
     fattori
    0.52
    humidité
    0.51
     sodium
    0.50
     մ
    0.50
    ⵚ
    0.50
     मिरची
    0.47
     rappresenta
    0.47
     Sodium
    0.47
     convinc
    0.47
     เฉล
    0.46
    Activations Density 0.001%

    No Known Activations