© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15434
    Prev
    Next
    INDEX
    Explanations

    a, with verbs and adjectives nearby

    oai_token-act-pair · gemini-2.0-flash

    references to physicality

    np_token-act-pair-logits · gpt-4o-mini

    Negative state or change of state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     فريبيس
    -0.65
    mybatisplus
    -0.64
    GOTREF
    -0.60
     المعيارى
    -0.54
     Paglinawan
    -0.52
    Referenced
    -0.44
     berangkat
    -0.44
    étricas
    -0.43
    IDENTAL
    -0.42
    fır
    -0.42
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.68
    esModule
    0.65
     physical
    0.65
    
    0.64
    İstinadlar
    0.64
    physical
    0.62
    \{\\
    0.62
     Physical
    0.61
     actionPerformed
    0.60
     الحره
    0.60
    Activations Density 1.154%

    No Known Activations