© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10988
    Prev
    Next
    INDEX
    Explanations

    specifications of car engines, including numerical values for engine size, number of cylinders, and the use of inch or liter for measurement.

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ########.
    -0.63
    Източници
    -0.59
    ---*/
    -0.57
    IntoConstraints
    -0.54
     prieten
    -0.54
    WithMany
    -0.53
     normaux
    -0.52
     vänner
    -0.52
     }}"></
    -0.52
    IsContent
    -0.51
    POSITIVE LOGITS
    webElementXpaths
    0.54
    GOTREF
    0.54
    Javadoc
    0.45
    idum
    0.45
    viewWillAppear
    0.45
    XmlAccessType
    0.44
    स्य
    0.44
     puestos
    0.44
     shut
    0.43
    startActivity
    0.43
    Activations Density 0.378%

    No Known Activations