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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14808
    Prev
    Next
    INDEX
    Explanations

    words that mean commonplace, or unspecific

    oai_token-act-pair · gemini-2.0-flash

    general

    np_max-act · gemini-2.0-flash

    general

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     large
    -0.85
     common
    -0.84
     high
    -0.82
     various
    -0.80
     recent
    -0.77
     specific
    -0.77
     potential
    -0.77
     great
    -0.76
     newly
    -0.75
     ſmall
    -0.75
    POSITIVE LOGITS
    <bos>
    1.53
    RegressionTest
    0.78
    Referanser
    0.73
     lanjut
    0.60
     समीक्षक
    0.59
     nakalista
    0.59
     Numerade
    0.57
     propOrder
    0.57
     chegou
    0.57
    Referències
    0.56
    Activations Density 2.470%

    No Known Activations