© 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. 1384
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and formatting characters

    oai_token-act-pair · gemini-2.0-flash

    detects computer code snippets

    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
     The
    -0.56
     but
    -0.53
    .
    -0.52
     
    -0.52
     What
    -0.49
     '
    -0.49
    ,
    -0.49
     []
    -0.46
    '
    -0.46
     (
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.96
    tvguidetime
    0.96
     MainAxisSize
    0.95
    ViewFeatures
    0.93
    
    0.88
    adaptiveStyles
    0.88
     surla
    0.88
    RegressionTest
    0.87
     насељу
    0.87
     myſelf
    0.87
    Activations Density 1.161%

    No Known Activations