© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15227
    Prev
    Next
    INDEX
    Explanations

    code blocks

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ftagPool
    -0.60
    +#+#
    -0.54
     boj
    -0.50
    rungsseite
    -0.49
     Robinson
    -0.48
    KeyName
    -0.48
     Pro
    -0.47
    happ
    -0.47
    stop
    -0.46
     Ste
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.79
     myſelf
    0.75
     Jefus
    0.70
     ſeveral
    0.68
    Tikang
    0.68
     fubject
    0.68
     Shakspeare
    0.67
     greateſt
    0.66
     reaſon
    0.64
     femininas
    0.63
    Activations Density 0.564%

    No Known Activations