© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10342
    Prev
    Next
    INDEX
    Explanations

    numerical data and words associated with limits or boundaries in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "after"

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

    after

    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
     HasFactory
    -0.77
    Datuak
    -0.66
    XmlEnum
    -0.59
    цездатний
    -0.58
     beginnetje
    -0.58
    ConstraintMaker
    -0.57
    "]();
    -0.56
     getRule
    -0.56
     então
    -0.56
    setVerticalGroup
    -0.55
    POSITIVE LOGITS
     after
    1.98
    after
    1.72
     после
    1.52
     після
    1.48
     After
    1.48
    After
    1.47
    AFTER
    1.39
     dopo
    1.35
     AFTER
    1.34
     após
    1.30
    Activations Density 1.945%

    No Known Activations