© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6598
    Prev
    Next
    INDEX
    Explanations

    personal opinions and attitudes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     him
    -2.17
     he
    -2.03
    He
    -1.81
    him
    -1.72
     He
    -1.64
    他
    -1.57
     он
    -1.56
     él
    -1.56
     ihn
    -1.52
     Him
    -1.43
    POSITIVE LOGITS
     propOrder
    0.91
    Jeografia
    0.90
     समीक्षाएं
    0.84
    ChildScrollView
    0.84
     فريبيس
    0.81
     समीक्षाओं
    0.77
    setVerticalGroup
    0.76
    Ї
    0.76
    ftagPool
    0.70
    تقاوى
    0.69
    Activations Density 1.814%

    No Known Activations