© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6079
    Prev
    Next
    INDEX
    Explanations

    references to leaning and bowing

    oai_token-act-pair · gemini-2.0-flash

    Leaning forward

    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
     ujednoznacz
    -0.78
     שוליים
    -0.75
    ftagPool
    -0.74
    SourceChecksum
    -0.70
     pinulongan
    -0.65
    niająca
    -0.65
    parsedMessage
    -0.63
    aarrggbb
    -0.63
     NSCoder
    -0.63
    AFX
    -0.62
    POSITIVE LOGITS
     fully
    0.55
     forward
    0.47
    forward
    0.46
     front
    0.45
     weight
    0.44
     edge
    0.43
     St
    0.42
    Hướng
    0.42
    weight
    0.42
     leaning
    0.42
    Activations Density 0.818%

    No Known Activations