Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1045
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "but", especially those followed by words indicating a change of mind

    oai_token-act-pair · gemini-2.0-flash

    But

    np_token-act-pair-logits · gemini-2.0-flash

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     للاسماء
    -0.85
    脚注の使い方
    -0.75
    
    -0.75
     kaarangay
    -0.73
     Efq
    -0.73
     CreateTagHelper
    -0.71
    principalColumn
    -0.68
    StoryboardSegue
    -0.68
     Autorisations
    -0.66
    发表于
    -0.65
    POSITIVE LOGITS
     kole
    0.49
    morphic
    0.47
    FormBuilder
    0.46
    fass
    0.44
    arbox
    0.41
    Search
    0.41
     Search
    0.41
    chieben
    0.41
    LineColor
    0.40
     Dr
    0.40
    Activations Density 1.603%

    No Known Activations