© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14268
    Prev
    Next
    INDEX
    Explanations

    pronouns and related words such as "have" and "would"

    oai_token-act-pair · gemini-2.0-flash

    I/we

    np_max-act-logits · 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
     bezeichneter
    -0.63
    contentLoaded
    -0.44
     ベクトル
    -0.42
     vetro
    -0.40
     apla
    -0.39
     systematically
    -0.39
    ил
    -0.39
     systé
    -0.38
    system
    -0.38
    ся
    -0.38
    POSITIVE LOGITS
    ftagPool
    0.88
    sidemargin
    0.78
    UIControlState
    0.71
    theoremstyle
    0.68
    脚注の使い方
    0.67
     ModelExpression
    0.66
    LElement
    0.65
    ConverterFactory
    0.65
    classnames
    0.65
    Notae
    0.64
    Activations Density 0.693%

    No Known Activations