© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    complex language relating to academic writing

    oai_token-act-pair · gemini-2.0-flash

    take

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    دانشنامهٔ
    -0.75
    indest
    -0.71
     ویکی‌پدیای
    -0.66
     الرخصة
    -0.65
    Personendaten
    -0.64
     lenker
    -0.63
     المعيارى
    -0.63
    )++;
    -0.62
    RegressionTest
    -0.61
     Audiodateien
    -0.59
    POSITIVE LOGITS
     take
    0.62
     TAKE
    0.55
    TAKE
    0.55
     Take
    0.53
    Take
    0.52
     took
    0.51
    take
    0.49
     takes
    0.49
    Taking
    0.47
     taking
    0.47
    Activations Density 4.050%

    No Known Activations