© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12221
    Prev
    Next
    INDEX
    Explanations

    mentions of numbered sections and forms

    oai_token-act-pair · gemini-2.0-flash

    section

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     himſelf
    -0.79
     ſeveral
    -0.77
     tranſ
    -0.75
     Efq
    -0.75
     Jefus
    -0.73
     becauſe
    -0.73
     Carra
    -0.72
     fubject
    -0.72
     endregion
    -0.72
     itſelf
    -0.72
    POSITIVE LOGITS
     kasarigan
    0.68
    ing
    0.52
    WebVitals
    0.46
     AssemblyTitle
    0.44
    vidade
    0.40
    #
    0.38
     judiciales
    0.38
    上的
    0.38
    *@
    0.38
     geldig
    0.37
    Activations Density 7.335%

    No Known Activations