© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14205
    Prev
    Next
    INDEX
    Explanations

    words and numbers used in academic research papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     eneste
    -0.73
     seules
    -0.71
    styleType
    -0.68
     uniquement
    -0.66
     only
    -0.66
     seuls
    -0.66
     alleen
    -0.65
    only
    -0.64
     singola
    -0.63
     soltanto
    -0.60
    POSITIVE LOGITS
    AddHtmlAttribute
    0.56
    ArrowToggle
    0.56
     跳转至
    0.54
    IconModule
    0.52
     Reverso
    0.51
    
    0.50
     ControllerBase
    0.50
     predecess
    0.49
     kém
    0.48
     extra
    0.47
    Activations Density 5.990%

    No Known Activations