© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9074
    Prev
    Next
    INDEX
    Explanations

    the word "the" or "this" followed by a word related to time; more broadly, it seems to activate on common words in the beginning of a sentence

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     headband
    -0.53
    kembang
    -0.50
    zcze
    -0.50
     Extragalactic
    -0.49
    Directories
    -0.48
    Rhestr
    -0.48
     ashtray
    -0.48
    塁
    -0.47
    expandindo
    -0.47
    रिक
    -0.46
    POSITIVE LOGITS
    +#+#
    0.74
    MigrationBuilder
    0.63
     تعدى
    0.60
     Bioaccumulative
    0.59
     consultato
    0.57
    AndEndTag
    0.57
    انيف
    0.57
    DispatchToProps
    0.56
     pinulongan
    0.56
    inghouse
    0.56
    Activations Density 1.379%

    No Known Activations