© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12242
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related words, such as "my", "her", "his", "our", "a" and the

    oai_token-act-pair · gemini-2.0-flash

    Personal spaces/belongings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ngths
    -0.52
    ContentLoaded
    -0.46
    visit
    -0.46
     visitó
    -0.44
     rég
    -0.43
    acial
    -0.43
    ويات
    -0.43
     Bowman
    -0.43
     coper
    -0.43
    Pyx
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.68
    windowFixed
    0.59
     houſe
    0.58
    IsContent
    0.58
     кӀ
    0.56
    LookAnd
    0.56
    ADELPHIA
    0.54
    parsedMessage
    0.53
    cèse
    0.53
     living
    0.52
    Activations Density 1.379%

    No Known Activations