© 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. 5893
    Prev
    Next
    INDEX
    Explanations

    common and proper nouns

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    initComponents
    -0.71
    Vidite
    -0.64
    LayoutStyle
    -0.63
    principalColumn
    -0.62
     actionPerformed
    -0.62
    onViewCreated
    -0.60
    postmedia
    -0.60
    fattning
    -0.59
     Савезне
    -0.59
    RetentionPolicy
    -0.59
    POSITIVE LOGITS
     ever
    0.66
    MigrationBuilder
    0.56
     very
    0.56
     wait
    0.54
     pièce
    0.53
     equivalent
    0.52
     epitome
    0.52
     créativité
    0.50
     Iconic
    0.50
     fameux
    0.49
    Activations Density 2.163%

    No Known Activations