© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15291
    Prev
    Next
    INDEX
    Explanations

    mentions of rings, specifically related to jewelry, sports equipment, or currency, and it sometimes triggers on a mention of a floor

    oai_token-act-pair · gemini-2.0-flash

    ring

    np_max-act · gemini-2.0-flash

    ring

    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
     the
    -1.01
    ↵↵
    -1.00
     A
    -0.96
     
    -0.95
     and
    -0.93
     in
    -0.91
    ↵
    -0.89
     a
    -0.86
     an
    -0.85
     at
    -0.83
    POSITIVE LOGITS
     مشين
    1.52
     bezeichneter
    1.48
    writeFieldEnd
    1.46
     nakalista
    1.45
    脚注の使い方
    1.38
    InputBorder
    1.38
    +#+#
    1.34
    
    1.34
    rungsseite
    1.33
    aarrggbb
    1.32
    Activations Density 1.189%

    No Known Activations