© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1479
    Prev
    Next
    INDEX
    Explanations

    sections of a document related to soccer teams, statistics, and categories

    oai_token-act-pair · gemini-2.0-flash

    Website-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     yet
    -0.47
    underset
    -0.46
     material
    -0.44
     proposed
    -0.42
    ↵
    -0.42
     tomorrow
    -0.42
     yes
    -0.41
     i
    -0.41
     min
    -0.41
    mb
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    1.12
     فريبيس
    0.96
     виправивши
    0.96
    OGND
    0.94
     HasFactory
    0.93
     utafitiHapana
    0.90
    Geplaatst
    0.88
     kaynağından
    0.85
     jScrollPane
    0.84
     المعيارى
    0.84
    Activations Density 0.146%

    No Known Activations