© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14467
    Prev
    Next
    INDEX
    Explanations

    code and code comments

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ModelExpression
    -0.66
    出版年
    -0.63
    MLLoader
    -0.55
     insuffisamment
    -0.50
    CreateMap
    -0.49
     MainAxisSize
    -0.48
    expandindo
    -0.47
    SourceChecksum
    -0.47
    esh
    -0.45
     DialogResult
    -0.43
    POSITIVE LOGITS
    statement
    0.57
    would
    0.56
     inoxydable
    0.54
    requirements
    0.54
    above
    0.54
    successor
    0.52
    ftance
    0.52
    Which
    0.51
    operation
    0.50
    should
    0.50
    Activations Density 14.202%

    No Known Activations