© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    the word "bear" and its inflections.

    oai_token-act-pair · gemini-2.0-flash

    bear

    np_max-act · 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
     bear
    -1.73
     bears
    -1.47
     Bear
    -1.47
    Bear
    -1.44
     bearing
    -1.44
     BEAR
    -1.38
    bear
    -1.36
    bears
    -1.26
     Bearing
    -1.23
    bearing
    -1.20
    POSITIVE LOGITS
    adaptiveStyles
    0.59
    Externí
    0.59
    примеча
    0.52
    లాలు
    0.52
    Бележки
    0.51
    newswire
    0.50
     CreateTagHelper
    0.49
    antMatchers
    0.48
    Autoritní
    0.47
    منابع
    0.47
    Activations Density 6.093%

    No Known Activations