© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5354
    Prev
    Next
    INDEX
    Explanations

    the word "bother" and words that share a semantic relationship with it like concern, dismay, tugging at heartstrings, etc

    oai_token-act-pair · gemini-2.0-flash

    bother

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     unwillingness
    -0.65
     mxArray
    -0.64
    viewDidLoad
    -0.60
     debatable
    -0.60
     disobedience
    -0.59
     suspicions
    -0.59
     problémy
    -0.58
    χρι
    -0.57
    StoryboardSegue
    -0.57
     hostility
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.67
     onBind
    0.59
     =>'
    0.59
    laterra
    0.59
     Garr
    0.58
    Доброго
    0.58
     Thad
    0.58
    elry
    0.56
    phat
    0.55
    huri
    0.55
    Activations Density 2.689%

    No Known Activations