© 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. 8507
    Prev
    Next
    INDEX
    Explanations

    text related to Canadian personal debt

    oai_token-act-pair · gemini-2.0-flash

    Canadian finance/government/education

    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
     realise
    -1.01
     minimise
    -0.99
     apologise
    -0.97
     specialises
    -0.96
     utilise
    -0.96
     realised
    -0.96
     recognises
    -0.95
     recognise
    -0.94
     Whilst
    -0.93
     apologised
    -0.92
    POSITIVE LOGITS
     toques
    0.67
     toque
    0.66
     Kij
    0.60
     amortization
    0.56
     legalization
    0.56
     Confederation
    0.55
     organization
    0.54
     immunization
    0.53
     mineralization
    0.53
     Grade
    0.53
    Activations Density 12.250%

    No Known Activations