© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12586
    Prev
    Next
    INDEX
    Explanations

    words used in scientific or technical contexts, possibly related to physics, engineering, or mathematics, identifying terminology associated with devices, processes, and analysis.

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     jouets
    -0.54
     touristes
    -0.47
     myö
    -0.46
     réc
    -0.45
     démocratie
    -0.44
    s
    -0.44
     oiseaux
    -0.44
     investissements
    -0.44
     deberes
    -0.43
     vinte
    -0.43
    POSITIVE LOGITS
    Portály
    0.92
     الحره
    0.79
     становника
    0.69
    AddHtmlAttribute
    0.65
    OGND
    0.64
    Rohy
    0.63
    titleMargin
    0.63
    ResponseWriter
    0.63
     كومونز
    0.60
    estination
    0.59
    Activations Density 9.969%

    No Known Activations