© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    code snippets with parentheses and function declarations

    oai_token-act-pair · gemini-2.0-flash

    code related identifiers

    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
     SED
    -1.07
     RD
    -1.05
     CSD
    -1.04
     GAD
    -1.02
     Kud
    -1.01
     SCD
    -1.00
     PCD
    -1.00
     SID
    -0.99
     VD
    -0.99
     PED
    -0.97
    POSITIVE LOGITS
     esternos
    0.52
    :✨
    0.47
    ViewFeatures
    0.46
     Baillargeon
    0.46
     ComVisible
    0.45
    FetchType
    0.44
    XmlAccessType
    0.41
     Italijanski
    0.40
    ftagPool
    0.39
    qtype
    0.38
    Activations Density 0.501%

    No Known Activations