© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11225
    Prev
    Next
    INDEX
    Explanations

    code or segments of code

    oai_token-act-pair · gemini-2.0-flash

    code outputs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.95
     للاسماء
    -0.66
    StructEnd
    -0.64
     disambiguazione
    -0.60
    etcode
    -0.60
     positifs
    -0.57
    ripsi
    -0.55
    נטרנט
    -0.55
     écrite
    -0.54
    JEE
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.54
    DoubleQuotes
    0.48
    modelBuilder
    0.48
     subsequence
    0.47
     TextInputType
    0.46
    pakah
    0.45
    =[[
    0.44
    sistence
    0.44
    knecht
    0.43
    ([[
    0.43
    Activations Density 1.473%

    No Known Activations