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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7299
    Prev
    Next
    INDEX
    Explanations

    verbs related to thinking, speaking, or acting

    oai_token-act-pair · gemini-2.0-flash

    Question answering/problem solving

    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
     
    -0.84
     '
    -0.66
     ‘
    -0.63
     new
    -0.52
     D
    -0.49
     $
    -0.48
     A
    -0.48
    i
    -0.48
    <strong>
    -0.48
     With
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.88
     Chwiliwch
    0.86
    ſelf
    0.85
     onCancelled
    0.84
     CURLOPT
    0.83
    WebVitals
    0.79
     bezeichneter
    0.79
    kloped
    0.79
    rrggbb
    0.78
     doubtnut
    0.78
    Activations Density 0.985%

    No Known Activations