© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7254
    Prev
    Next
    INDEX
    Explanations

    terms and values related to cricket batting statistics in code

    oai_token-act-pair · gemini-2.0-flash

    )

    np_max-act-logits · 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
    Negative Logits
    AddTagHelper
    -0.62
     Tests
    -0.55
     tests
    -0.53
    
    -0.53
     disambiguazione
    -0.52
    脚注の使い方
    -0.52
    estens
    -0.51
     testigo
    -0.51
    Tests
    -0.50
    ESTIC
    -0.50
    POSITIVE LOGITS
    IndentedString
    0.80
    tagHelperRunner
    0.59
    LEncoder
    0.57
    IsInitialized
    0.54
    ggiata
    0.54
    <bos>
    0.52
    🦯
    0.52
     consultato
    0.52
    cloudfront
    0.52
    lgari
    0.52
    Activations Density 0.298%

    No Known Activations