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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13929
    Prev
    Next
    INDEX
    Explanations

    mentions of mythical or imaginary figures with animalistic features.

    oai_token-act-pair · gemini-2.0-flash

    animal features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     للمعارف
    -0.52
     Heine
    -0.42
    offsetof
    -0.42
    wieś
    -0.41
    cjon
    -0.40
    HasAnnotation
    -0.40
     Trá
    -0.40
    nologue
    -0.40
     henvisninger
    -0.40
     SwiftUI
    -0.40
    POSITIVE LOGITS
     deer
    0.69
     CanadaChoose
    0.69
     raccoon
    0.68
     Centa
    0.68
     pter
    0.65
     chimpanze
    0.65
     rodent
    0.64
     scaly
    0.64
     feline
    0.61
     snout
    0.61
    Activations Density 2.767%

    No Known Activations