© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5400
    Prev
    Next
    INDEX
    Explanations

    what appears to be version numbers and web user agents

    oai_token-act-pair · gemini-2.0-flash

    Code and user agents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     الرياضيه
    -0.70
    المكان
    -0.58
    Билгалдахарш
    -0.55
     surla
    -0.52
     насељу
    -0.51
     فريبيس
    -0.51
    createCanvas
    -0.51
    setVerticalGroup
    -0.50
     Wicidata
    -0.50
    TestingModule
    -0.49
    POSITIVE LOGITS
    printStackTrace
    0.77
    VersionUID
    0.58
     Rücks
    0.57
    alip
    0.57
     Waray
    0.56
     MERCHANTABILITY
    0.55
     regress
    0.53
    CPtr
    0.52
    helin
    0.52
    userAgent
    0.52
    Activations Density 0.566%

    No Known Activations