© 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. 10611
    Prev
    Next
    INDEX
    Explanations

    references to nationalities and ethnicities

    oai_token-act-pair · gemini-2.0-flash

    nationalities

    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
    تقاوى
    -0.74
    UnknownFieldSet
    -0.66
    Personensuche
    -0.65
    LLocation
    -0.65
    ISupport
    -0.62
    Portale
    -0.62
    interopRequire
    -0.61
    Jereo
    -0.60
    contentLoaded
    -0.59
    CloseOperation
    -0.59
    POSITIVE LOGITS
     CSO
    0.55
    liflower
    0.54
    rogly
    0.52
     youth
    0.49
    alds
    0.48
     speakers
    0.48
     youths
    0.47
     intellectuals
    0.47
    èze
    0.47
     encroachment
    0.46
    Activations Density 1.105%

    No Known Activations