© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14919
    Prev
    Next
    INDEX
    Explanations

    occurrences of possessive pronouns, personal pronouns, and other words indicating the person involved in some action, especially "his" and "her".

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ]--;
    -0.65
     propOrder
    -0.61
    Demografía
    -0.60
    GroupLayout
    -0.59
    utilisons
    -0.59
    RefreshLayout
    -0.58
    yarnpkg
    -0.58
     pageContext
    -0.57
     Wiss
    -0.56
     ExecuteAsync
    -0.56
    POSITIVE LOGITS
     виправивши
    0.65
     tartalomajánló
    0.59
     sauvages
    0.58
    homonymie
    0.53
     mukana
    0.48
    źnie
    0.47
     médicaux
    0.47
     nonUne
    0.47
     fondament
    0.47
     sebou
    0.47
    Activations Density 13.502%

    No Known Activations