© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    text near formatting symbols or numerical lists

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     dzī
    -0.45
    sk
    -0.45
    .
    -0.44
    ,
    -0.44
     cottura
    -0.44
     médicaux
    -0.44
     capuche
    -0.43
     chré
    -0.43
     nemico
    -0.42
     häls
    -0.42
    POSITIVE LOGITS
     Th
    1.33
     Thi
    1.10
    Th
    1.06
     Tha
    1.01
     Ther
    0.98
    SequentialGroup
    0.96
    AsUp
    0.95
    Thi
    0.94
    Ҭ
    0.93
     th
    0.91
    Activations Density 4.195%

    No Known Activations