© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    text including unusual unicode characters

    oai_token-act-pair · gemini-2.0-flash

    special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    bootstrapcdn
    -0.71
     Италијани
    -0.71
    EIP
    -0.66
    出版年
    -0.66
    Dữ
    -0.66
    %");
    -0.65
     decathlon
    -0.63
    LabelTagHelper
    -0.63
    >");
    -0.62
    batore
    -0.62
    POSITIVE LOGITS
    ISupport
    0.46
     constantes
    0.43
     ujednoznacz
    0.41
     mesmas
    0.37
     enfans
    0.36
     specchio
    0.36
     rápidas
    0.36
    WithIdentifier
    0.36
     traités
    0.35
    Appearance
    0.35
    Activations Density 0.888%

    No Known Activations