© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    Hypertext Transfer Protocol (HTTP) or Hypertext Transfer Protocol Secure (HTTPS) web addresses

    oai_token-act-pair · gemini-2.0-flash

    http/https

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    twimg
    -0.72
    PreferredItem
    -0.68
    XmlAccessType
    -0.62
    UpInside
    -0.60
    Lähteet
    -0.60
    قایناق‌لار
    -0.58
    ⓧ
    -0.57
    TestBed
    -0.56
    tagext
    -0.55
    PickerController
    -0.54
    POSITIVE LOGITS
    Демографія
    0.67
     Parthen
    0.54
    palla
    0.52
     Idd
    0.52
     Italijanski
    0.47
     Sidd
    0.46
    ictured
    0.46
    жере
    0.46
    CppCodeGen
    0.46
     Cister
    0.46
    Activations Density 0.026%

    No Known Activations