© 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. 6200
    Prev
    Next
    INDEX
    Explanations

    code blocks in C

    oai_token-act-pair · gemini-2.0-flash

    words related to competition

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

    Competition

    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
     disambiguazione
    -0.94
     pinulongan
    -0.73
     utafitiHapana
    -0.70
     lenker
    -0.65
    rungsseite
    -0.64
    RenderAtEndOf
    -0.63
     Sedgwick
    -0.62
    ГЛА
    -0.62
    WebVitals
    -0.62
    TagHelpers
    -0.62
    POSITIVE LOGITS
     competitive
    0.93
    competitive
    0.84
     competitively
    0.78
     Competitive
    0.75
     competition
    0.74
     COMPET
    0.71
     competi
    0.71
    Competitive
    0.69
     competitivo
    0.66
     competitivos
    0.66
    Activations Density 0.729%

    No Known Activations