© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12539
    Prev
    Next
    INDEX
    Explanations

    the words "some" and "with" along with articles, possessives, or other linking words

    oai_token-act-pair · gemini-2.0-flash

    categories or classifications

    np_token-act-pair-logits · gpt-4o-mini

    some

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     joaat
    -0.52
     onCancelled
    -0.52
     épaules
    -0.51
     تعدى
    -0.50
     prêtres
    -0.50
     nuages
    -0.49
    Skocz
    -0.49
     flesta
    -0.49
     endregion
    -0.49
    tagHelperRunner
    -0.49
    POSITIVE LOGITS
     sorts
    0.69
     types
    0.67
     type
    0.64
     sort
    0.63
     kinds
    0.63
     aspects
    0.62
     layers
    0.61
     levels
    0.60
    TypedDataSet
    0.56
     decisions
    0.55
    Activations Density 6.034%

    No Known Activations