© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and formulas, as well as references to figures and tables, and measurements of physical dimensions, lengths and distances.

    oai_token-act-pair · gemini-2.0-flash

    Social, physical

    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
     slope
    -0.69
     Climb
    -0.65
     slopes
    -0.65
     hills
    -0.60
     climbs
    -0.60
     Slope
    -0.57
    वरी
    -0.57
     climb
    -0.57
    Incl
    -0.56
     grades
    -0.53
    POSITIVE LOGITS
     social
    0.59
     physical
    0.53
    MessageOf
    0.52
     соціаль
    0.51
     eventdata
    0.51
    ximity
    0.50
     BorderSide
    0.50
     actionPerformed
    0.50
     sosial
    0.50
     Physical
    0.49
    Activations Density 1.759%

    No Known Activations