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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6893
    Prev
    Next
    INDEX
    Explanations

    key turning points or breaking points in a situation

    oai_token-act-pair · gemini-2.0-flash

    tipping points or limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     retrouver
    -0.49
    WithIOException
    -0.48
    대로
    -0.48
    ministrazione
    -0.46
    PLICIT
    -0.46
    rufe
    -0.46
    ull
    -0.46
    Diwedd
    -0.45
    TIMEOUT
    -0.44
    authier
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.88
     itſelf
    0.59
     Signalez
    0.58
     NSCoder
    0.57
    DockStyle
    0.55
    עם
    0.54
    rungsseite
    0.52
    TagMode
    0.52
    expandindo
    0.52
    tubers
    0.52
    Activations Density 1.491%

    No Known Activations