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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15760
    Prev
    Next
    INDEX
    Explanations

    text that is separated from the surrounding text, possibly titles or headings

    oai_token-act-pair · gemini-2.0-flash

    words ending with "ſelf"

    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
    ↵↵
    -1.83
    ↵
    -1.26
    ↵↵↵
    -0.88
    ↵↵↵↵
    -0.68
     V
    -0.63
     
    -0.60
     M
    -0.59
     H
    -0.59
    ':
    -0.59
    ":
    -0.58
    POSITIVE LOGITS
     itſelf
    1.26
     pleaſure
    1.19
     greateſt
    1.09
     myſelf
    1.09
     himſelf
    1.08
     Monfieur
    1.07
     leſs
    1.04
     themſelves
    1.03
     ſeveral
    1.02
     ſche
    1.02
    Activations Density 2.547%

    No Known Activations