© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10846
    Prev
    Next
    INDEX
    Explanations

    capitalized words within sentences, especially those that appear to be company and product names

    oai_token-act-pair · gemini-2.0-flash

    business and company names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    witz
    -0.53
     rarely
    -0.43
    enburg
    -0.43
    taka
    -0.43
     much
    -0.42
     Ch
    -0.42
    mak
    -0.42
     â
    -0.42
     seldom
    -0.42
     $\
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.82
    ValueStyle
    0.82
     itſelf
    0.76
     myſelf
    0.71
    contentLoaded
    0.71
     purpoſe
    0.71
    IndentedString
    0.70
     pleaſure
    0.70
     الرياضيه
    0.69
    脚注の使い方
    0.69
    Activations Density 0.881%

    No Known Activations