© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3846
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    на
    2.31
    ق
    2.15
    ින්
    2.11
    tens
    1.95
    thema
    1.89
    h
    1.85
    тта
    1.83
    یز
    1.81
    ate
    1.78
    larda
    1.70
    POSITIVE LOGITS
     moguće
    1.89
     그렇지
    1.87
     согласно
    1.77
    定番
    1.75
    对待
    1.74
     zamanda
    1.70
    Й
    1.69
    commonly
    1.67
    ?[
    1.65
     mich
    1.64
    Activations Density 0.006%

    No Known Activations