© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14185
    Prev
    Next
    INDEX
    Explanations

    a complex combination of blog post metadata including URLs, HTML tags, and language about historical revisionism or investment advice.

    oai_token-act-pair · gemini-2.0-flash

    words indicating invitations or requests

    np_token-act-pair-logits · gpt-4o-mini

    blog snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    contentLoaded
    -0.79
    AutoScaleMode
    -0.78
    AndEndTag
    -0.77
     AssemblyCulture
    -0.77
    ContentAsync
    -0.75
    IntoConstraints
    -0.73
     Roskov
    -0.69
    enterOuterAlt
    -0.69
     OFDb
    -0.66
     nahilalakip
    -0.66
    POSITIVE LOGITS
     "
    0.47
     “
    0.47
     For
    0.47
    MISSIONS
    0.46
     od
    0.45
    IMENTO
    0.45
     Want
    0.45
     To
    0.45
     u
    0.44
     hit
    0.43
    Activations Density 3.894%

    No Known Activations