© 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. 9250
    Prev
    Next
    INDEX
    Explanations

    Irish names and references to Scottish or Irish history, chiefs, and estates.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     Vasquez
    -0.65
     Zimmermann
    -0.61
     Kuz
    -0.59
     Zimmerman
    -0.56
    PYX
    -0.56
    βολ
    -0.56
     vanadium
    -0.55
    VITA
    -0.53
     ZO
    -0.52
    RegistryLite
    -0.52
    POSITIVE LOGITS
     disambiguazione
    0.61
     '{@
    0.58
    dafx
    0.56
     فريبيس
    0.56
    homonymie
    0.55
     Audiodateien
    0.54
     ffilmiau
    0.53
     שוליים
    0.51
     Superhosts
    0.50
    wch
    0.50
    Activations Density 6.949%

    No Known Activations