© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209729
    Prev
    Next
    INDEX
    Explanations

    linked list node data

    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_19_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
     rats
    0.50
     Rats
    0.48
    伙
    0.48
    োর্টে
    0.47
    וא
    0.47
     ions
    0.46
     aguj
    0.46
    ത്തിയാ
    0.46
     holes
    0.45
     foxes
    0.45
    POSITIVE LOGITS
    દ
    0.49
    enu
    0.43
    方の
    0.42
    textFont
    0.42
    ステム
    0.40
    有個
    0.39
     teritor
    0.39
    debugElement
    0.39
    createElement
    0.38
    insertBefore
    0.38
    Activations Density 0.004%

    No Known Activations