© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    figure references, color names, and highlighted words

    oai_token-act-pair · gemini-2.0-flash

    red arrow

    np_max-act · gemini-2.0-flash

    red

    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_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
    tvguidetime
    -0.81
     dél
    -0.65
    Demografia
    -0.63
    脚注の使い方
    -0.62
     délé
    -0.62
     modalités
    -0.62
     gesteld
    -0.61
     community
    -0.61
     abbigliamento
    -0.60
     poils
    -0.59
    POSITIVE LOGITS
     toep
    0.73
     chunky
    0.71
     snob
    0.69
    polated
    0.62
     lovers
    0.62
     darn
    0.62
    INSEE
    0.60
     tapered
    0.60
     thick
    0.60
     thicker
    0.58
    Activations Density 4.117%

    No Known Activations