© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8643
    Prev
    Next
    INDEX
    Explanations

    code-related words, especially words connected to confirming accounts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     confirmation
    -2.52
     confirm
    -2.41
     Confirmation
    -2.33
     confirming
    -2.30
     Confirm
    -2.28
    confirm
    -2.20
     confirmations
    -2.19
    Confirmation
    -2.14
     confirmed
    -2.13
     confirms
    -2.11
    POSITIVE LOGITS
     contextLoads
    0.71
     con
    0.63
     InputDecoration
    0.61
    ViewImports
    0.50
     IBOutlet
    0.50
    writeField
    0.49
     GenerationType
    0.48
    UCKY
    0.46
    Pot
    0.43
     Pot
    0.43
    Activations Density 3.103%

    No Known Activations