© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8314
    Prev
    Next
    INDEX
    Explanations

    non-English words and internet addresses, possibly related to a specific language

    oai_token-act-pair · gemini-2.0-flash

    Foreign conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     dan
    -0.64
     myſelf
    -0.60
     Roskov
    -0.60
    abestanden
    -0.57
     ejus
    -0.57
     iſt
    -0.56
     geb
    -0.53
    ſelf
    -0.52
     ſon
    -0.52
    nuevos
    -0.51
    POSITIVE LOGITS
     lipat
    0.57
     esfuer
    0.57
    ufnahme
    0.56
     kalangan
    0.55
    INCREF
    0.55
    rippa
    0.55
     setelan
    0.54
     økonom
    0.52
    навли
    0.51
     lukisan
    0.51
    Activations Density 0.641%

    No Known Activations