© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4784
    Prev
    Next
    INDEX
    Explanations

    java and asv source code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pan
    -1.72
     PAN
    -1.65
     Pan
    -1.59
    Pan
    -1.51
    PAN
    -1.50
    pan
    -1.47
     pans
    -1.37
    pans
    -1.30
     Pans
    -1.28
    pane
    -1.11
    POSITIVE LOGITS
    expandindo
    0.47
     Quig
    0.42
     Detroit
    0.42
    ViewFeatures
    0.41
    <eos>
    0.41
    K
    0.40
     trofeo
    0.40
     @"/
    0.40
     climati
    0.40
     letto
    0.40
    Activations Density 0.421%

    No Known Activations