© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7652
    Prev
    Next
    INDEX
    Explanations

    the names of countries in the Americas and words relating to the Americas

    oai_token-act-pair · gemini-2.0-flash

    America

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Amerikan
    -0.81
    ADELPHIA
    -0.78
     américains
    -0.76
     American
    -0.72
    cticut
    -0.71
    Connecticut
    -0.69
    American
    -0.69
    Atsauces
    -0.68
    LANTA
    -0.66
     barbati
    -0.66
    POSITIVE LOGITS
     فريبيس
    0.66
     imageNamed
    0.60
    msgTypes
    0.59
     AssemblyVersion
    0.58
    acro
    0.55
     jspb
    0.53
     Stoll
    0.52
    ::_('
    0.52
    zzleHttp
    0.52
     Manga
    0.52
    Activations Density 0.304%

    No Known Activations