© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    mentions of something happening multiple times

    oai_token-act-pair · gemini-2.0-flash

    number of occurrences

    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
    IntoConstraints
    -0.75
     متعلقه
    -0.74
    EndGlobalSection
    -0.73
     كومونز
    -0.68
    Coordonnées
    -0.66
    Autoritní
    -0.64
     jScrollPane
    -0.64
    bufio
    -0.62
    
    -0.58
     الرياضيه
    -0.57
    POSITIVE LOGITS
     once
    2.20
     twice
    2.00
    once
    1.94
    twice
    1.83
    Twice
    1.80
    Once
    1.78
     ONCE
    1.73
     Once
    1.71
     Twice
    1.70
     times
    1.65
    Activations Density 2.041%

    No Known Activations