© 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. 10637
    Prev
    Next
    INDEX
    Explanations

    mentions of wanting information, along with names of people and countries

    oai_token-act-pair · gemini-2.0-flash

    possess

    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
    MLLoader
    -0.73
    DeleteBehavior
    -0.69
    RegressionTest
    -0.67
    ⓧ
    -0.64
     ModelExpression
    -0.64
    новниш
    -0.63
    webElementXpaths
    -0.63
    الإنجليزية
    -0.63
    GEBURTSDATUM
    -0.63
    ScopeManager
    -0.61
    POSITIVE LOGITS
     possess
    1.46
     possession
    1.38
     possesses
    1.36
     posses
    1.35
    poss
    1.27
     possessing
    1.27
     possessed
    1.25
     Poss
    1.21
    Poss
    1.21
    possession
    1.17
    Activations Density 1.682%

    No Known Activations