© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10779
    Prev
    Next
    INDEX
    Explanations

    code or data structures, which often include curly braces, brackets, and associated keywords.

    oai_token-act-pair · gemini-2.0-flash

    Non-English words

    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
     off
    -0.47
     terms
    -0.47
     the
    -0.47
    ↵
    -0.46
     leading
    -0.45
     
    -0.45
    h
    -0.44
     first
    -0.44
     once
    -0.44
     Simon
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.18
    Vidite
    1.11
     nakalista
    1.05
    abestanden
    1.03
     متعلقه
    0.99
    VIAF
    0.98
     виправивши
    0.98
     Roskov
    0.94
    LookAnd
    0.91
     autorytatywna
    0.91
    Activations Density 0.475%

    No Known Activations