© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    personal possessions/space

    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
     Audiodateien
    -0.63
    onomía
    -0.56
    routeProvider
    -0.53
     {},
    -0.52
     correctes
    -0.52
     estekak
    -0.52
     iParam
    -0.52
    trum
    -0.50
     Valverde
    -0.50
    ubehör
    -0.50
    POSITIVE LOGITS
     незавершена
    0.64
    conomie
    0.47
     Hilde
    0.46
     grotte
    0.44
    Географиясе
    0.44
    GroupLayout
    0.44
    webElementXpaths
    0.44
     '\\;'
    0.44
     Wahrnehmung
    0.42
    tention
    0.42
    Activations Density 0.512%

    No Known Activations