© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8389
    Prev
    Next
    INDEX
    Explanations

    image files in HTML

    oai_token-act-pair · gemini-2.0-flash

    Image URLs and HTML

    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
     year
    -0.57
     bağ
    -0.49
     once
    -0.49
    ify
    -0.48
    (
    -0.48
    lah
    -0.45
    жи
    -0.45
    çant
    -0.45
    umą
    -0.45
     ahead
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.84
    verwijspagina
    0.77
    httphttps
    0.76
     disambiguazione
    0.71
    Parcelize
    0.70
     חיצוניים
    0.69
    NewUrlParser
    0.68
    istoitu
    0.68
    TagHelper
    0.66
     lenker
    0.66
    Activations Density 1.500%

    No Known Activations