© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9021
    Prev
    Next
    INDEX
    Explanations

    technical or medical information

    oai_token-act-pair · gemini-2.0-flash

    medical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Hozzáférés
    -0.59
    JspWriter
    -0.56
    ioutil
    -0.55
     @"/
    -0.54
    delwed
    -0.49
     AspNetCore
    -0.49
    )++;
    -0.48
     linkovi
    -0.48
    tagHelperRunner
    -0.45
     Mal
    -0.45
    POSITIVE LOGITS
     متعلقه
    0.55
     utafitiHapana
    0.54
     ویکی‌پدیای
    0.53
    VersionUID
    0.52
     BoxFit
    0.49
     bire
    0.48
     peggio
    0.48
    DropColumn
    0.48
    Opposite
    0.46
    RegisterType
    0.45
    Activations Density 2.824%

    No Known Activations