© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7444
    Prev
    Next
    INDEX
    Explanations

    technical words related to model airplanes and measuring the properties of resins

    oai_token-act-pair · gemini-2.0-flash

    propellers and fans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ächs
    -0.47
    kanen
    -0.44
    sinh
    -0.44
    cosh
    -0.43
    XmlAccessType
    -0.43
    СТВ
    -0.41
     INF
    -0.40
    East
    -0.40
     typelib
    -0.40
     linkovi
    -0.40
    POSITIVE LOGITS
     blades
    0.81
     motor
    0.80
     fans
    0.78
     propeller
    0.77
     fan
    0.76
     Spin
    0.75
    Motor
    0.74
     spinning
    0.74
    motor
    0.74
     blade
    0.74
    Activations Density 1.300%

    No Known Activations