© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15398
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes.

    oai_token-act-pair · gemini-2.0-flash

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    span
    -1.43
     span
    -1.07
    SPAN
    -0.97
    Span
    -0.91
     spans
    -0.89
     Span
    -0.88
    <bos>
    -0.87
    spans
    -0.85
     SPAN
    -0.79
    SourceChecksum
    -0.72
    POSITIVE LOGITS
    Hochspringen
    0.69
    ANTLR
    0.60
    
    0.55
    expandindo
    0.52
    Odor
    0.51
     StatefulWidget
    0.50
    ).__
    0.50
     UnityEditor
    0.49
    Einzelnachweise
    0.49
     kaynağından
    0.48
    Activations Density 7.948%

    No Known Activations