© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6530
    Prev
    Next
    INDEX
    Explanations

    mathematical and contractual terminology.

    oai_token-act-pair · gemini-2.0-flash

    code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ú
    -0.56
    ù
    -0.55
    UNIT
    -0.50
    uban
    -0.50
    URL
    -0.49
    RUP
    -0.48
    NU
    -0.48
    URA
    -0.48
    Unit
    -0.48
     University
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.69
     resourceCulture
    0.60
     Мексичка
    0.60
    AfterClass
    0.59
    rungsseite
    0.58
     saites
    0.58
     Wikimedijinoj
    0.58
    (!__
    0.58
     Roskov
    0.57
    Portale
    0.56
    Activations Density 3.599%

    No Known Activations