© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4348
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, showing no clear pattern

    oai_token-act-pair · gemini-2.0-flash

    extent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    EDEFAULT
    -0.62
    GEBURTSDATUM
    -0.58
    #+#
    -0.58
    TRAILING
    -0.56
    kloped
    -0.54
    FormTagHelper
    -0.54
    tanleria
    -0.53
    AsUp
    -0.52
    出版年
    -0.52
    servez
    -0.49
    POSITIVE LOGITS
     wider
    1.54
     broad
    1.52
     wide
    1.52
     widened
    1.49
     widen
    1.48
     expanded
    1.46
     broadened
    1.45
     widest
    1.45
     broaden
    1.43
     range
    1.41
    Activations Density 6.840%

    No Known Activations