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. 946
    Prev
    Next
    INDEX
    Explanations

    scientific text describing vector mathematics in the context of physics

    oai_token-act-pair · gemini-2.0-flash

    z

    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
     habet
    -0.52
    diva
    -0.51
    apimachinery
    -0.50
     sê
    -0.49
    grès
    -0.48
     peur
    -0.47
    uoš
    -0.47
    কার
    -0.47
     minuten
    -0.47
    باط
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.83
    LabelTagHelper
    0.66
    DebuggerStep
    0.62
    Зноскі
    0.58
    {}",
    0.58
     שוליים
    0.55
     tartalomajánló
    0.55
    #+#
    0.55
    Enllaços
    0.54
     باخ
    0.54
    Activations Density 1.549%

    No Known Activations