© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6542
    Prev
    Next
    INDEX
    Explanations

    words and contexts related to investigations of accidents

    oai_token-act-pair · gemini-2.0-flash

    terms related to wreckage and incidents

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

    plane crashes/accidents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iNdEx
    -0.60
    __);
    -0.60
    .*")]
    -0.57
    HomeAsUpEnabled
    -0.56
    __':
    -0.54
     الدولى
    -0.54
     forState
    -0.53
     فريبيس
    -0.53
    исленность
    -0.53
     mena
    -0.52
    POSITIVE LOGITS
    ManagedBean
    0.52
    crity
    0.51
    JAKARTA
    0.46
     ویکی‌پدیا
    0.43
    aragus
    0.43
    GPP
    0.42
     companhia
    0.41
     wreckage
    0.41
    QtWidgets
    0.41
    Wey
    0.41
    Activations Density 1.028%

    No Known Activations