© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 436
    Prev
    Next
    INDEX
    Explanations

    words used in discussions of computer code

    oai_token-act-pair · gemini-2.0-flash

    desde

    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
     BoxFit
    -0.60
     localVar
    -0.59
     Nie
    -0.57
     Baillargeon
    -0.57
     nahilalakip
    -0.57
    Климат
    -0.54
    然
    -0.54
     Hardly
    -0.54
     pinulongan
    -0.54
    CopyWith
    -0.54
    POSITIVE LOGITS
     pleaſure
    0.55
    RegressionTest
    0.51
    $}}
    0.50
     purpoſe
    0.50
    ImageContext
    0.47
     vosotros
    0.47
     uſed
    0.45
    posedge
    0.45
     culprit
    0.44
    asyarakat
    0.44
    Activations Density 0.497%

    No Known Activations