© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15269
    Prev
    Next
    INDEX
    Explanations

    question marks and bullet points within quotes

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ,
    -1.11
    .
    -0.96
    )
    -0.47
    -
    -0.43
    '
    -0.39
    :
    -0.32
    That
    -0.31
    One
    -0.30
    To
    -0.29
     комите
    -0.28
    POSITIVE LOGITS
    ChildScrollView
    1.22
    findpost
    1.12
    FormTagHelper
    1.12
    IsContent
    1.11
    webElementXpaths
    1.09
    DockStyle
    1.07
    />";
    1.07
    TagMode
    1.06
    BeginContext
    1.02
    ContentAsync
    1.02
    Activations Density 6.397%

    No Known Activations