© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    mathematical and software engineering notation

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    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
     lenker
    -0.66
    findpost
    -0.63
    RectangleBorder
    -0.57
     //$
    -0.56
     extré
    -0.54
    ServletException
    -0.54
    vespa
    -0.54
    Suara
    -0.53
     ProtoMessage
    -0.53
     Complement
    -0.52
    POSITIVE LOGITS
     gauche
    0.50
     mẽ
    0.47
     iNdEx
    0.47
    logits
    0.46
    isLoaded
    0.46
    شویی
    0.44
     Lohan
    0.44
     Fath
    0.44
     cherchés
    0.43
    WHEREAS
    0.43
    Activations Density 8.934%

    No Known Activations