© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14622
    Prev
    Next
    INDEX
    Explanations

    HTML image links and related tags surrounding the images

    oai_token-act-pair · gemini-2.0-flash

    img

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    img
    -0.55
     charité
    -0.54
     marinho
    -0.54
     marins
    -0.52
     abiye
    -0.50
    ListModule
    -0.50
     occidentale
    -0.49
     sej
    -0.49
     cathédrale
    -0.49
     tunik
    -0.47
    POSITIVE LOGITS
     calendriers
    0.63
     שוליים
    0.63
     للمعارف
    0.63
    CppMethod
    0.63
     незавершена
    0.59
    Enllaces
    0.59
    Bronnen
    0.59
     &___
    0.58
     nakalista
    0.57
    errHandler
    0.56
    Activations Density 1.527%

    No Known Activations