© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3482
    Prev
    Next
    INDEX
    Explanations

    capitalized words, acronyms, or words with a similar pattern of capitalization, and words relating to speed

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    rungsseite
    -0.84
     GenerationType
    -0.76
    CodeDom
    -0.75
    sidemargin
    -0.74
    ]--;
    -0.65
     corretamente
    -0.61
     manches
    -0.60
    ophan
    -0.60
    ArgumentParser
    -0.60
     Riproduzione
    -0.60
    POSITIVE LOGITS
    AndEndTag
    0.62
     sharp
    0.57
    SharedDtor
    0.56
    fast
    0.55
     attentive
    0.54
     intelligent
    0.54
     strong
    0.53
     stable
    0.53
     fast
    0.52
     expressive
    0.52
    Activations Density 0.924%

    No Known Activations