© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    references to international codes, patents, or taxonomic classifications.

    oai_token-act-pair · gemini-2.0-flash

    international

    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
     protoimpl
    -0.60
    StateList
    -0.47
     combineReducers
    -0.46
    alab
    -0.45
     Accesat
    -0.45
     Ministerio
    -0.44
     ministerio
    -0.44
    abestanden
    -0.44
     œufs
    -0.43
     Ministry
    -0.41
    POSITIVE LOGITS
     International
    1.29
    International
    1.20
     international
    1.20
    international
    1.16
     internationale
    1.13
     INTERNATIONAL
    1.13
    国际
    1.09
    INTERNATIONAL
    1.07
     internacional
    1.05
     internationalen
    1.03
    Activations Density 1.486%

    No Known Activations