© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    dates separated by forward slashes, parentheses, hyphens, and other punctuation, likely representing date formats

    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
    ategy
    -0.51
     CreateTagHelper
    -0.50
     endfor
    -0.49
    trak
    -0.44
     useStyles
    -0.44
    ించ
    -0.43
    غول
    -0.43
    
    -0.42
    estries
    -0.42
    itura
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.92
    tagHelperRunner
    0.63
    queryInterface
    0.59
    Rhestr
    0.59
    oredCriteria
    0.57
    Jeografia
    0.55
     riuscito
    0.54
    FailureListener
    0.53
     Administrativna
    0.53
     répar
    0.52
    Activations Density 3.425%

    No Known Activations