© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9607
    Prev
    Next
    INDEX
    Explanations

    Java import statements and related keywords

    oai_token-act-pair · gemini-2.0-flash

    javax

    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
     javax
    -1.33
    javax
    -0.80
     convertView
    -0.61
    <bos>
    -0.57
    AppComponent
    -0.55
    Tē
    -0.50
     BERNAMA
    -0.50
    struts
    -0.47
    følgelig
    -0.47
     userSchema
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.61
    KommentareTeilen
    0.57
    piles
    0.56
    AddTagHelper
    0.55
    DotNetBar
    0.54
    ята
    0.53
     laterale
    0.52
     Otra
    0.52
    ">//
    0.52
     Administrativna
    0.51
    Activations Density 0.858%

    No Known Activations