© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13974
    Prev
    Next
    INDEX
    Explanations

    the word "you" together with words "if", "can", “want”, or "to".

    oai_token-act-pair · gemini-2.0-flash

    you

    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
    hof
    -0.46
     convertView
    -0.45
    newtheorem
    -0.42
    rcParams
    -0.40
     ut
    -0.40
     ud
    -0.39
     Z
    -0.39
     demostr
    -0.38
    рус
    -0.38
     Larsson
    -0.38
    POSITIVE LOGITS
    MLLoader
    0.93
    GEBURTSDATUM
    0.93
     Wikimedijinoj
    0.90
     autorytatywna
    0.87
    parsedMessage
    0.85
    complexContent
    0.84
     للمعارف
    0.82
     AssemblyTitle
    0.81
     ModelExpression
    0.79
    RenderAtEndOf
    0.77
    Activations Density 1.777%

    No Known Activations