© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2464
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words associated with them, particularly place names and software names

    oai_token-act-pair · gemini-2.0-flash

    Places and ethnicities

    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
     actionTypes
    -0.57
     SearchView
    -0.52
     sơ
    -0.50
    Referanser
    -0.50
     CallOverrides
    -0.47
    Demografie
    -0.45
     cáo
    -0.45
    bestimmungen
    -0.45
    \}\\
    -0.44
    олові
    -0.43
    POSITIVE LOGITS
    المناصب
    0.64
    MLLoader
    0.62
    ThroughAttribute
    0.61
    SBATCH
    0.59
    Хьажоргаш
    0.58
    SPJ
    0.57
     betweenstory
    0.56
    ISupport
    0.55
     extern
    0.54
    PRODUC
    0.54
    Activations Density 1.066%

    No Known Activations