© 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. 5414
    Prev
    Next
    INDEX
    Explanations

    HTML option tags, file locations, version numbers, and changes to code

    oai_token-act-pair · gemini-2.0-flash

    code and location data

    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
     ([
    -0.57
    ([
    -0.53
     $[
    -0.50
    www
    -0.50
    Попис
    -0.50
     [
    -0.47
     &[
    -0.46
     hueso
    -0.45
     reflecting
    -0.45
     rosto
    -0.44
    POSITIVE LOGITS
     propOrder
    0.72
    ConstraintMaker
    0.69
    ManagedBean
    0.64
    VersionUID
    0.63
    TagMode
    0.63
     JpaRepository
    0.60
    ScopeManager
    0.60
     useHistory
    0.59
    IntoConstraints
    0.58
    gameserver
    0.58
    Activations Density 0.445%

    No Known Activations