© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3834
    Prev
    Next
    INDEX
    Explanations

    words or characters followed by identifiers such as colons, parentheses or quotes

    oai_token-act-pair · gemini-2.0-flash

    eponymous and related words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    tvguidetime
    -0.64
    setVerticalGroup
    -0.54
    setDo
    -0.48
    BorderWidth
    -0.44
    เฉ
    -0.43
    +#+#
    -0.41
    SqlSession
    -0.41
     nécessairement
    -0.40
    RegressionTest
    -0.39
     vorrei
    -0.39
    POSITIVE LOGITS
     Epid
    0.61
    Архівовано
    0.60
     Bhd
    0.60
     Instinct
    0.58
     Efq
    0.57
     IRIS
    0.57
     trapez
    0.56
     Ulysses
    0.55
     Trimble
    0.55
    enumii
    0.54
    Activations Density 4.646%

    No Known Activations