© 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. 13913
    Prev
    Next
    INDEX
    Explanations

    instances of the "implements" or "extends" keywords

    oai_token-act-pair · gemini-2.0-flash

    extends/implements

    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
    Negative Logits
    tvguidetime
    -0.75
    таратура
    -0.63
     itſelf
    -0.60
    ')
    -0.60
     ſind
    -0.60
    iastes
    -0.59
    '},
    -0.59
     myſelf
    -0.59
    sinki
    -0.59
     Camin
    -0.59
    POSITIVE LOGITS
     صوتيه
    0.79
    AddTagHelper
    0.66
     impide
    0.58
    fjspx
    0.57
    StoryboardSegue
    0.57
    InvalidProtocol
    0.57
     GONNA
    0.56
     Taxation
    0.56
     Gonna
    0.55
     Shee
    0.54
    Activations Density 0.087%

    No Known Activations