© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10437
    Prev
    Next
    INDEX
    Explanations

    descriptions of fasteners or adhesives

    oai_token-act-pair · gemini-2.0-flash

    loop/sensitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     diary
    -0.75
     journal
    -0.69
     diaries
    -0.67
     journals
    -0.61
     logs
    -0.58
    日志
    -0.58
     pinulongan
    -0.57
     diário
    -0.56
     Diary
    -0.56
     dziennik
    -0.56
    POSITIVE LOGITS
     reinstalled
    0.60
    ✨:
    0.57
    intios
    0.54
     חיצוניים
    0.54
    IsContent
    0.54
    writeFieldEnd
    0.54
     reinstalling
    0.53
    oa̍t
    0.53
    évaluateur
    0.53
    原始内容存档于
    0.53
    Activations Density 0.584%

    No Known Activations