© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 13601
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of people and places in India, as well as political parties.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCulture
    -0.71
    DeleteBehavior
    -0.62
     ExecuteAsync
    -0.61
    (&:
    -0.59
    Geplaatst
    -0.57
     springfox
    -0.56
    oredCriteria
    -0.56
    tangentMode
    -0.55
    elemField
    -0.53
    Demografía
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.61
    )');
    0.53
    spricht
    0.49
     &___
    0.47
    τύ
    0.46
     Kons
    0.45
    )");
    
    0.44
     too
    0.44
    bald
    0.44
    )");
    0.43
    Activations Density 1.562%

    No Known Activations