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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 697
    Prev
    Next
    INDEX
    Explanations

    newline characters and the characters that immediately proceed them

    oai_token-act-pair · gemini-2.0-flash

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Akismet
    -0.50
     pageable
    -0.49
    AnimationsModule
    -0.49
    OrNil
    -0.47
    AtIndexPath
    -0.46
    евна
    -0.45
     chisel
    -0.45
    Naissance
    -0.44
    flickr
    -0.44
     Perseus
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.84
    WebVitals
    0.64
    rungsseite
    0.64
    帖最后由
    0.61
     snippetHide
    0.60
    audiovisuel
    0.55
    حوالہ
    0.54
     sekali
    0.54
    enterOuterAlt
    0.54
     heard
    0.50
    Activations Density 3.214%

    No Known Activations