© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1799
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and nouns, especially "his", "its", "their", and names ending in 's

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     للاسماء
    -0.82
     AssemblyTitle
    -0.65
     themſelves
    -0.64
     varandra
    -0.62
    })();
    -0.61
    SharedCtor
    -0.61
     zichzelf
    -0.60
     itſelf
    -0.60
     gärna
    -0.58
     zelve
    -0.57
    POSITIVE LOGITS
    jsxFileName
    0.61
    ModelAdmin
    0.60
    AccessException
    0.60
    +#+#
    0.58
     StatefulWidget
    0.56
     column
    0.56
    PreAuthorize
    0.54
     parents
    0.52
     father
    0.50
     Wikimedijinoj
    0.50
    Activations Density 1.574%

    No Known Activations