© 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. 9215
    Prev
    Next
    INDEX
    Explanations

    statistics and numbers within parentheses

    oai_token-act-pair · gemini-2.0-flash

    female subjects or study statistics

    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
    Rüyada
    -0.51
    sizeCache
    -0.51
    RegistryLite
    -0.49
     air
    -0.47
    IonicModule
    -0.47
    ViewFeatures
    -0.46
    CDATA
    -0.46
     deco
    -0.45
    ArrowToggle
    -0.44
    Brainz
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.82
     ivelany
    0.60
     الوطنيه
    0.56
     født
    0.56
    borderSide
    0.55
     bParam
    0.54
     mérit
    0.54
     mérite
    0.52
     deserve
    0.52
    asthan
    0.51
    Activations Density 0.831%

    No Known Activations