© 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. 5962
    Prev
    Next
    INDEX
    Explanations

    many variations of the word "take" and words frequently found around it, like "a", "of", "my", "time", "forever", "more", "than", and "year"

    oai_token-act-pair · gemini-2.0-flash

    take

    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
    ImageContext
    -0.63
    KURZBESCHREIBUNG
    -0.57
     čierna
    -0.55
    ElementException
    -0.52
     correctes
    -0.52
     varandra
    -0.49
     geldig
    -0.49
     skolan
    -0.47
     caduta
    -0.46
    parseColor
    -0.46
    POSITIVE LOGITS
     its
    0.71
     uska
    0.65
    subplots
    0.63
    Портал
    0.60
    WEBPACK
    0.59
     time
    0.57
    kháu
    0.57
     all
    0.56
    upto
    0.55
    orda
    0.54
    Activations Density 2.123%

    No Known Activations