© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    opinion pieces with strong sentiment in complete sentences, with some technical or financial jargon.

    oai_token-act-pair · 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
    nyttet
    -0.60
     oprot
    -0.49
     Remarque
    -0.49
    cristo
    -0.48
     Londra
    -0.47
     bitte
    -0.47
    UserScript
    -0.47
    ीय
    -0.45
    ThroughAttribute
    -0.45
    TestBase
    -0.45
    POSITIVE LOGITS
    lwjgl
    0.65
    mybatisplus
    0.65
    ComponentScan
    0.57
     protoimpl
    0.54
    ExecuteReader
    0.53
     snippetHide
    0.52
    出版年
    0.52
    matchCondition
    0.52
    rungsseite
    0.51
    saraba
    0.51
    Activations Density 1.976%

    No Known Activations