© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    UK business and accounting terms

    oai_token-act-pair · gemini-2.0-flash

    Bright and colorful

    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
     subsidy
    -0.77
     warrant
    -0.75
     debt
    -0.73
     warranty
    -0.71
     funding
    -0.70
     contract
    -0.70
     reimbursement
    -0.69
     subsidies
    -0.68
     liability
    -0.68
     permission
    -0.68
    POSITIVE LOGITS
     bright
    0.58
     kaarangay
    0.57
     inspiré
    0.54
    +#+#
    0.52
     vibr
    0.50
     brightly
    0.50
     colorful
    0.50
     styled
    0.48
     lovely
    0.48
     amazing
    0.48
    Activations Density 4.600%

    No Known Activations