© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7803
    Prev
    Next
    INDEX
    Explanations

    words related to conditional logic or options

    oai_token-act-pair · gemini-2.0-flash

    choosing appropriate action

    np_max-act-logits · 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
    Appropriate
    -2.27
     Appropriate
    -2.20
     appropriate
    -2.19
     suitable
    -2.16
    appropriate
    -2.11
    suitable
    -2.09
     Suitable
    -1.98
    Suitable
    -1.89
     unsuitable
    -1.57
     suited
    -1.55
    POSITIVE LOGITS
    
    0.70
     UITableViewCell
    0.57
     EClass
    0.56
    setObjectName
    0.54
    Finals
    0.50
     getItemId
    0.48
    avyzd
    0.48
     EconPapers
    0.48
    antd
    0.47
    LEncoder
    0.47
    Activations Density 3.974%

    No Known Activations