© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    words related to duration, existence, and value

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Whenever
    -1.77
    Whenever
    -1.76
    whenever
    -1.71
     whenever
    -1.64
    WHEN
    -1.43
     WHEN
    -1.36
    when
    -1.30
     When
    -1.28
    quando
    -1.27
    When
    -1.25
    POSITIVE LOGITS
    diel
    0.52
    enance
    0.49
    γγε
    0.47
     continuing
    0.45
     &_
    0.41
    */),
    0.41
    getTop
    0.41
    abond
    0.40
    consulté
    0.40
    AddHtmlAttribute
    0.40
    Activations Density 3.230%

    No Known Activations