© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14635
    Prev
    Next
    INDEX
    Explanations

    code syntax like commas, parentheses, asterisks, and brackets

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     мәкал
    -0.71
    Aholisi
    -0.65
    Попис
    -0.63
     DMG
    -0.60
    期刊论文
    -0.60
    KURZBESCHREIBUNG
    -0.58
     Réponses
    -0.57
     ویکی‌پدی
    -0.57
     collectons
    -0.57
    IUrlHelper
    -0.56
    POSITIVE LOGITS
     ModelExpression
    0.77
     الحره
    0.51
     nothing
    0.48
    ಿಕ
    0.47
     كومونز
    0.47
     everything
    0.44
    gebung
    0.44
    everything
    0.44
    стр
    0.44
     menyer
    0.43
    Activations Density 0.716%

    No Known Activations