© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12787
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    oai_token-act-pair · gemini-2.0-flash

    Acronyms/abbreviations

    np_max-act · gemini-2.0-flash

    acronyms

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.68
    jsdelivr
    -0.61
    UrlResolution
    -0.57
    ficulty
    -0.52
    >((
    -0.49
    cloudflare
    -0.48
     GlobalKey
    -0.46
    LST
    -0.45
    IMPORTED
    -0.45
     lenker
    -0.45
    POSITIVE LOGITS
     vierge
    0.69
     Gazetteer
    0.69
    Rüyada
    0.68
     feroit
    0.66
     图库
    0.66
     alrededores
    0.66
     blessés
    0.64
     
    0.63
     regionales
    0.63
     nationaux
    0.63
    Activations Density 1.259%

    No Known Activations