© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6049
    Prev
    Next
    INDEX
    Explanations

    mentions of worth or elements in legal or review documents

    oai_token-act-pair · gemini-2.0-flash

    value or components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <eos>
    -0.65
    ↵↵
    -0.63
    ↵
    -0.63
     a
    -0.61
    …
    -0.59
     an
    -0.58
     just
    -0.55
     
    -0.52
    form
    -0.51
     form
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    1.00
    Chham
    0.96
    AndEndTag
    0.96
    protoimpl
    0.92
     Efq
    0.92
    ImageContext
    0.90
     Euphrates
    0.90
     Jefus
    0.88
     defaultstate
    0.88
    rungsseite
    0.88
    Activations Density 0.641%

    No Known Activations