© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2643
    Prev
    Next
    INDEX
    Explanations

    sentences that discusses the difficulties, suffering, and general experience of people and groups of people from a variety of possible causes and places.

    oai_token-act-pair · gemini-2.0-flash

    context about suffering and consequences

    np_token-act-pair-logits · gpt-4o-mini
    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
     disambiguazione
    -0.66
     berke
    -0.55
    seurs
    -0.55
    ullah
    -0.49
    Глава
    -0.49
    Bibliograf
    -0.49
     gyhoeddwyd
    -0.49
    xtick
    -0.47
    getDoctrine
    -0.47
     незавершена
    -0.47
    POSITIVE LOGITS
     مشين
    0.61
    BeginContext
    0.56
    numerusform
    0.53
    )_/¯
    0.50
    mism
    0.49
    RectangleBorder
    0.48
     verke
    0.48
     <>",
    0.48
    Falls
    0.48
     ***!
    0.47
    Activations Density 4.189%

    No Known Activations