© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    source code snippets, lists, and structured data like names and dates.

    oai_token-act-pair · gemini-2.0-flash

    Technical/structured information

    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
    ,
    -0.65
    ↵
    -0.62
    -
    -0.58
     
    -0.56
    .
    -0.54
    :
    -0.54
     '
    -0.53
     ‘
    -0.52
     (
    -0.50
    ;
    -0.50
    POSITIVE LOGITS
     feroit
    1.49
     étoit
    1.49
     pouvoit
    1.43
     auroit
    1.42
     avoient
    1.40
     فريبيس
    1.34
     étoient
    1.31
     ainfi
    1.27
     dévelo
    1.23
     Efq
    1.18
    Activations Density 56.932%

    No Known Activations