© 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. 3894
    Prev
    Next
    INDEX
    Explanations

    passages of dialogue

    oai_token-act-pair · gemini-2.0-flash

    Agreement words

    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
     useAuth
    -0.57
    AddHtmlAttribute
    -0.54
    Према
    -0.52
    ."""
    -0.48
    .
    -0.48
     ***/
    -0.47
    이버
    -0.46
    enumi
    -0.46
     GSA
    -0.46
    러나
    -0.45
    POSITIVE LOGITS
     ok
    0.61
    例文帳に追加
    0.60
    tagHelperRunner
    0.60
     OK
    0.60
    ennia
    0.59
    RegressionTest
    0.57
     AssemblyTitle
    0.56
     Yes
    0.56
     Okay
    0.55
    gnition
    0.55
    Activations Density 2.540%

    No Known Activations