© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12794
    Prev
    Next
    INDEX
    Explanations

    characters and syntax common in code and data tables.

    oai_token-act-pair · gemini-2.0-flash

    terms associated with grouping or categorization

    np_token-act-pair-logits · gpt-4o-mini

    Organizational structure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    zyż
    -0.56
    ValueStyle
    -0.54
    ->___
    -0.51
     saluto
    -0.51
     démission
    -0.50
    لكتر
    -0.49
     prétend
    -0.48
    ismet
    -0.46
     fakta
    -0.46
     mergeFrom
    -0.45
    POSITIVE LOGITS
     group
    0.81
     program
    0.71
     channel
    0.64
     unit
    0.63
     site
    0.63
     zone
    0.63
     organization
    0.62
     category
    0.60
     page
    0.60
    group
    0.60
    Activations Density 10.832%

    No Known Activations