© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10863
    Prev
    Next
    INDEX
    Explanations

    numbers including numbers paired with a currency symbol

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     fourteen
    -0.81
     sixteen
    -0.78
     twelve
    -0.77
     Fourteen
    -0.73
     thirteen
    -0.67
     nine
    -0.67
     Twelve
    -0.66
    Twelve
    -0.65
     Sixteen
    -0.63
     seventeen
    -0.61
    POSITIVE LOGITS
    0
    0.81
    5
    0.79
    WithIOException
    0.76
    MessageOf
    0.67
    bitField
    0.61
    expandindo
    0.61
     InputDecoration
    0.60
     виправивши
    0.58
     متعلقه
    0.57
     ModelExpression
    0.56
    Activations Density 5.908%

    No Known Activations