© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7839
    Prev
    Next
    INDEX
    Explanations

    words related to technical and functional specifications

    oai_token-act-pair · gemini-2.0-flash

    spec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     spec
    -2.41
    Spec
    -2.31
    spec
    -2.31
     Spec
    -2.27
    SPEC
    -2.03
     specification
    -2.00
     SPEC
    -1.94
     Specification
    -1.91
    Specification
    -1.80
     specs
    -1.80
    POSITIVE LOGITS
     ComVisible
    0.75
    tonsoft
    0.75
    parsedMessage
    0.75
     himo
    0.75
     BoxFit
    0.74
    setVerticalGroup
    0.71
    tvguidetime
    0.71
    audiovisuel
    0.71
    ChildScrollView
    0.70
    EndGlobalSection
    0.69
    Activations Density 1.049%

    No Known Activations