© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11800
    Prev
    Next
    INDEX
    Explanations

    discussions including people's names who are experiencing mental, emotional, or psychological challenges or trauma .

    oai_token-act-pair · gemini-2.0-flash

    dealing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    cloudfront
    -0.69
    richTextPanel
    -0.68
    IsPostBack
    -0.63
    Besos
    -0.61
    таратура
    -0.59
    Bronnen
    -0.57
    rénées
    -0.57
    ccoli
    -0.56
     yii
    -0.56
    WebControls
    -0.55
    POSITIVE LOGITS
     dealing
    1.28
     Dealing
    1.22
     deal
    1.20
    deal
    1.20
     DEAL
    1.13
    Dealing
    1.11
     deals
    1.11
    Deal
    1.06
     Deal
    1.05
     dealt
    1.02
    Activations Density 1.515%

    No Known Activations