© 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. 7499
    Prev
    Next
    INDEX
    Explanations

    a mix of common words, punctuation, and formatting sometimes associated with business, law, or sports reporting.

    oai_token-act-pair · gemini-2.0-flash

    legal, company names

    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
    Portály
    -0.60
    NOPQRST
    -0.55
     BioLib
    -0.53
     Magne
    -0.52
     Fedor
    -0.52
     AssemblyTitle
    -0.51
     Kog
    -0.51
     TAC
    -0.50
     Dordrecht
    -0.50
     Gog
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.75
    Brainz
    0.67
    الإنجليزية
    0.65
    />";
    0.63
    IsMutable
    0.59
     continúas
    0.57
     समीक्षक
    0.57
    Nazionale
    0.56
    السكان
    0.56
    वरण
    0.56
    Activations Density 1.286%

    No Known Activations