© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1500
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuing to read something

    oai_token-act-pair · gemini-2.0-flash

    blog post snippets

    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
    ("$.
    -0.49
     fractionation
    -0.47
     perchance
    -0.44
     militari
    -0.43
    bool
    -0.42
    ีก
    -0.42
     vele
    -0.42
     spons
    -0.42
     natürlich
    -0.41
    Leider
    -0.40
    POSITIVE LOGITS
     Normdatei
    0.82
    MENAFN
    0.81
    EndContext
    0.79
    \}\\
    0.78
    WebVitals
    0.76
    XmlEnum
    0.75
     ویکی‌پدیای
    0.75
    Geplaatst
    0.74
     بيها
    0.73
    istoitu
    0.72
    Activations Density 2.111%

    No Known Activations