© 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. 5702
    Prev
    Next
    INDEX
    Explanations

    capitalized single letters or short letter combinations

    oai_token-act-pair · gemini-2.0-flash

    technical identifiers or terms

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

    Scientific publications/citations

    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
     confounding
    -0.57
     Vea
    -0.54
    WithIOException
    -0.53
     powders
    -0.52
     pyruvate
    -0.51
    лючение
    -0.50
     powder
    -0.50
     chandelier
    -0.49
     invariance
    -0.49
    ProgressHUD
    -0.48
    POSITIVE LOGITS
     الاطلاع
    0.62
     ModelExpression
    0.50
    GEBURTSDATUM
    0.50
     استنادى
    0.48
    Espèce
    0.48
    NOPQRST
    0.48
    Odkazy
    0.48
    Архівовано
    0.46
     Tech
    0.46
    OrBuilder
    0.46
    Activations Density 0.315%

    No Known Activations