© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87094
    Prev
    Next
    INDEX
    Explanations

    Jenga and Walters

    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_3_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
    лд
    0.66
    "
    0.61
    洛
    0.59
    $
    0.56
    뭡
    0.56
    л
    0.55
    essen
    0.54
    racellular
    0.54
    伶
    0.54
    ст
    0.53
    POSITIVE LOGITS
    ing
    0.83
     Mayıs
    0.77
    ться
    0.70
     expérience
    0.70
     pensamento
    0.70
     menurunkan
    0.68
     incremento
    0.68
    ת
    0.67
    بین
    0.66
    it
    0.65
    Activations Density 0.000%

    No Known Activations