© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4432
    Prev
    Next
    INDEX
    Explanations

    words related to duration, speed, and intensity

    oai_token-act-pair · gemini-2.0-flash

    Descriptions and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Going
    -1.18
     Taking
    -1.10
     Talking
    -1.09
     Heading
    -1.09
     Looking
    -1.08
     Working
    -1.07
     Sitting
    -1.07
    Going
    -1.06
     Running
    -1.04
    Taking
    -1.04
    POSITIVE LOGITS
    CodeAttribute
    0.56
     GeoNames
    0.53
     ویکی‌پدیا
    0.50
    StateToProps
    0.50
    FromNib
    0.49
    Demikian
    0.48
     Möglichkeit
    0.47
     JpaRepository
    0.47
     समीक्षाओं
    0.47
    trường
    0.46
    Activations Density 15.076%

    No Known Activations