© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data analysis and computer operations

    oai_token-act-pair · gemini-2.0-flash

    By means of

    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
    ukone
    -0.60
     BoxDecoration
    -0.60
    IntoConstraints
    -0.57
     GeoNames
    -0.52
     --;
    -0.51
    Välislingid
    -0.51
    shund
    -0.51
    Comun
    -0.51
     الرياضيه
    -0.50
     Huskies
    -0.50
    POSITIVE LOGITS
     via
    1.59
    via
    1.27
     through
    1.27
     using
    1.27
     través
    1.22
     mediante
    1.22
     tramite
    1.19
     melalui
    1.18
    Via
    1.12
     através
    1.12
    Activations Density 5.428%

    No Known Activations