© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5316
    Prev
    Next
    INDEX
    Explanations

    code blocks with indentation and curly braces

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     VIAF
    -0.60
     الحره
    -0.57
    WebElementEntity
    -0.56
     zvuky
    -0.55
    StoryboardSegue
    -0.54
    etle
    -0.54
    UserScript
    -0.51
    اس
    -0.50
     Sitten
    -0.50
    }))
    -0.50
    POSITIVE LOGITS
        
    0.58
    AccessorTable
    0.56
    ipedi
    0.52
     seven
    0.51
    APOLIS
    0.51
    ⓧ
    0.51
     sieben
    0.49
    SharedCtor
    0.48
    mium
    0.48
     SEVEN
    0.48
    Activations Density 1.595%

    No Known Activations