© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated terms including titles, ages, medical codes, arrows, and discourse analysis terms

    oai_token-act-pair · gemini-2.0-flash

    Duke

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    цездатний
    -0.80
    adpleegd
    -0.75
    sidemargin
    -0.74
    SharedCtor
    -0.74
    OGND
    -0.73
    IndentedString
    -0.72
    InputTagHelper
    -0.72
     Monfieur
    -0.72
    parsedMessage
    -0.69
    tanleria
    -0.68
    POSITIVE LOGITS
    En
    0.44
    mdash
    0.42
    tis
    0.41
    ById
    0.40
     Pollard
    0.40
     Hecht
    0.39
     extra
    0.39
     hopefully
    0.39
    Cy
    0.39
    eclipse
    0.39
    Activations Density 8.386%

    No Known Activations