© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    phrases using "in that" to connect ideas

    oai_token-act-pair · gemini-2.0-flash

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     pleaſure
    -0.71
     uſe
    -0.69
     purpoſe
    -0.64
     uſed
    -0.64
     Theſe
    -0.60
     ſta
    -0.60
     ſtand
    -0.59
     faſt
    -0.57
     myſelf
    -0.56
     Conſ
    -0.55
    POSITIVE LOGITS
    :+:
    0.68
    ReusableCell
    0.60
     '\\;'
    0.56
    ########.
    0.56
    '])){
    0.55
    BrowserModule
    0.54
    )));
    0.54
    WindowConstants
    0.52
     deg
    0.51
    ChildScrollView
    0.50
    Activations Density 3.131%

    No Known Activations