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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10499
    Prev
    Next
    INDEX
    Explanations

    words in a language other than English, possibly Slavic languages

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    Izvori
    -0.64
     holotype
    -0.54
    ftagPool
    -0.52
     volcanoes
    -0.50
    moteur
    -0.50
    SharedCtor
    -0.49
     muualla
    -0.49
     exemplaires
    -0.49
     Tätigkeit
    -0.48
     dėl
    -0.47
    POSITIVE LOGITS
    thâu
    0.57
    copic
    0.57
    RenderAtEndOf
    0.56
    ########.
    0.55
    weta
    0.55
     برانيه
    0.53
    erus
    0.51
    eaway
    0.51
    diman
    0.51
    Kaieteur
    0.50
    Activations Density 0.067%

    No Known Activations