© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6448
    Prev
    Next
    INDEX
    Explanations

    code blocks or code snippets

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming constructs

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

    code

    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
    competitive
    -1.05
     competitive
    -1.05
     competition
    -0.90
     Competitive
    -0.88
    Competitive
    -0.84
     competitively
    -0.83
     competitivos
    -0.82
     competi
    -0.81
     competitions
    -0.80
    Competi
    -0.80
    POSITIVE LOGITS
     pinulongan
    0.63
    SharedCtor
    0.60
    FirstResponder
    0.57
    phanie
    0.57
    RenderAtEndOf
    0.57
    ICAN
    0.56
     Orto
    0.56
    MatIconModule
    0.56
    ⎨
    0.55
    assan
    0.55
    Activations Density 2.363%

    No Known Activations