© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9806
    Prev
    Next
    INDEX
    Explanations

    words expressing problems or something out of order

    oai_token-act-pair · gemini-2.0-flash

    Something is wrong

    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
     étoit
    -0.70
     étoient
    -0.66
     scolaires
    -0.65
     enfans
    -0.63
    الدراسه
    -0.63
     vectorielles
    -0.63
     fidé
    -0.63
     avoient
    -0.63
     createState
    -0.62
    setVerticalGroup
    -0.62
    POSITIVE LOGITS
    #+#
    0.56
     שוליים
    0.48
    atguigu
    0.44
     lat
    0.44
    bber
    0.44
     πά
    0.44
     A
    0.43
    PageModule
    0.43
    landet
    0.43
     haj
    0.43
    Activations Density 0.636%

    No Known Activations