© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3798
    Prev
    Next
    INDEX
    Explanations

    computer code or data

    oai_token-act-pair · gemini-2.0-flash

    computer science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    itemBuilder
    -0.52
    пой
    -0.50
    ктан
    -0.49
    penup
    -0.49
     spot
    -0.47
    mstyle
    -0.46
    wix
    -0.45
     ří
    -0.45
    libft
    -0.44
    ?
    -0.44
    POSITIVE LOGITS
     المعيارى
    0.73
     ErrIntOverflow
    0.64
     дописавши
    0.63
     насељу
    0.63
     estimés
    0.62
    BibitemShut
    0.60
     nahilalakip
    0.58
     Wiktionnaire
    0.57
     MainAxisSize
    0.57
    "]);
    0.56
    Activations Density 0.199%

    No Known Activations