© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10272
    Prev
    Next
    INDEX
    Explanations

    scores in sports games

    oai_token-act-pair · gemini-2.0-flash

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GraphicsUnit
    -0.69
    WriteBarrier
    -0.68
    openzeppelin
    -0.60
    httphttps
    -0.60
    ollectionView
    -0.59
     fifty
    -0.58
    lyk
    -0.58
     sixty
    -0.57
     kasarigan
    -0.56
    expandindo
    -0.55
    POSITIVE LOGITS
     păr
    0.61
    IUrlHelper
    0.57
     toimi
    0.55
     vectorielle
    0.51
     kanssa
    0.50
     PVA
    0.50
     Baillargeon
    0.50
     Squal
    0.49
    )++;
    0.49
     BPI
    0.49
    Activations Density 2.248%

    No Known Activations