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. 1017
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash

    questions asking "is there" or making comparisons/clarifications (e.g., "or").

    oai_token-act-pair · gemini-2.0-flash

    or

    np_token-act-pair-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
    }$​
    -0.68
    !")
    
    -0.66
    ?
    
    -0.65
    BibitemShut
    -0.63
     للاسماء
    -0.62
     itſelf
    -0.61
    %?
    -0.60
     unseen
    -0.60
     ་་
    -0.60
    )"),
    -0.60
    POSITIVE LOGITS
     or
    0.69
     oppure
    0.65
     whether
    0.61
     OR
    0.57
     Or
    0.53
     and
    0.53
     Whether
    0.52
    有無
    0.51
    whether
    0.51
    是否
    0.51
    Activations Density 1.207%

    No Known Activations