© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11272
    Prev
    Next
    INDEX
    Explanations

    information about Italian athletes, especially cyclists and footballers, including their names, teams, and places of origin

    oai_token-act-pair · gemini-2.0-flash

    Italian language tokens or phrases

    np_token-act-pair-logits · gpt-4o-mini

    Italian 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Efq
    -0.93
     Monfieur
    -0.93
     متعلقه
    -0.86
    iprot
    -0.85
     незавершена
    -0.84
     myſelf
    -0.84
     itſelf
    -0.83
     titolata
    -0.82
     Majefty
    -0.82
     AssemblyCompany
    -0.80
    POSITIVE LOGITS
     di
    0.78
     della
    0.66
     dei
    0.57
     delle
    0.56
     dell
    0.54
     gia
    0.54
    azz
    0.52
     Italia
    0.52
     Италии
    0.50
     Gio
    0.50
    Activations Density 12.517%

    No Known Activations