© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13225
    Prev
    Next
    INDEX
    Explanations

    technical medical reports and diagnoses

    oai_token-act-pair · gemini-2.0-flash

    Medical complications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     continúas
    -0.52
    oja
    -0.49
     wach
    -0.49
    lass
    -0.48
     **)
    -0.47
    SUITE
    -0.46
     jLabel
    -0.45
    Geplaatst
    -0.45
     /\.(
    -0.45
    ℗
    -0.45
    POSITIVE LOGITS
    Captor
    0.72
     Ngb
    0.56
     فريبيس
    0.56
    ArrowToggle
    0.54
     ArrayAdapter
    0.54
    IVEREF
    0.54
     heapq
    0.53
     مشين
    0.53
     indentation
    0.52
    AutoScale
    0.52
    Activations Density 3.774%

    No Known Activations