© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14301
    Prev
    Next
    INDEX
    Explanations

    horizontal lines in tables or code, and also anything to do with items or durations, possibly on a dashboard

    oai_token-act-pair · gemini-2.0-flash

    horizontal lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     fusca
    -0.66
    ثيق
    -0.65
     ſtand
    -0.62
     fellowships
    -0.61
     ſhe
    -0.61
    viewDidLoad
    -0.60
     Rink
    -0.59
     hearing
    -0.59
    шое
    -0.58
     Fod
    -0.58
    POSITIVE LOGITS
    Попис
    0.64
    
    0.62
     transfieras
    0.59
     estekak
    0.57
     ++;
    0.55
    ChromeDriver
    0.54
    AndEndTag
    0.54
     ErrIntOverflow
    0.53
    tagHelperRunner
    0.50
    ranton
    0.50
    Activations Density 0.735%

    No Known Activations