© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11313
    Prev
    Next
    INDEX
    Explanations

    words related to logic or reasoning

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'times'

    np_token-act-pair-logits · gpt-4o-mini

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RegressionTest
    -0.50
     তারিখ
    -0.48
     voldoende
    -0.43
     الدولى
    -0.43
     ?",
    -0.43
    ChildScrollView
    -0.41
    
    -0.41
    Backbone
    -0.41
     =>
    -0.41
    越好
    -0.40
    POSITIVE LOGITS
     times
    1.94
     twice
    1.93
     Twice
    1.80
    twice
    1.76
    Twice
    1.66
    Times
    1.55
     TIMES
    1.51
     Times
    1.51
     thrice
    1.42
     TWICE
    1.41
    Activations Density 2.616%

    No Known Activations