© 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. 4920
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "ive," or words beginning with "re" and also having "ct" in positions matching the example words

    oai_token-act-pair · gemini-2.0-flash

    academic/technical language

    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
     consultato
    -0.73
     lccn
    -0.73
     surla
    -0.70
    脚注の使い方
    -0.67
     CanadaChoose
    -0.66
     TextAppearance
    -0.66
    ViewImports
    -0.66
    HttpFoundation
    -0.65
    Rujuakan
    -0.65
     dAtA
    -0.65
    POSITIVE LOGITS
    ions
    0.57
    ons
    0.55
    ion
    0.48
    ive
    0.47
    jon
    0.45
    anal
    0.45
    onal
    0.45
    oned
    0.44
    ron
    0.44
    он
    0.43
    Activations Density 1.583%

    No Known Activations