© 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
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 587
    Prev
    Next
    INDEX
    Explanations

    fourth, third, and numbers

    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_38_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
    二是
    0.66
    second
    0.63
    SECOND
    0.56
    ②
    0.56
     seconda
    0.55
     השני
    0.55
     ikinci
    0.55
    ➋
    0.55
    Second
    0.54
     second
    0.53
    POSITIVE LOGITS
     fourth
    0.61
     चौथी
    0.59
     Third
    0.59
    Third
    0.55
    第四
    0.54
     third
    0.54
     quatrième
    0.53
     चौथे
    0.53
    Fourth
    0.52
     Fourth
    0.52
    Activations Density 0.072%

    No Known Activations