© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 251234
    Prev
    Next
    INDEX
    Explanations

    statistically

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     significantly
    1.05
     substantially
    1.04
     Significantly
    0.99
     considerably
    0.93
     значительно
    0.91
     существенно
    0.83
     deutlich
    0.78
     p
    0.76
     wesentlich
    0.75
     appreciably
    0.72
    POSITIVE LOGITS
    life
    0.43
     LIFE
    0.43
    Association
    0.42
    LIFE
    0.41
    (${
    0.41
     ASSOCIATION
    0.40
     life
    0.40
    INCLUDING
    0.39
    Life
    0.38
     SWITCH
    0.38
    Activations Density 0.001%

    No Known Activations