© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13473
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns and family relationships or close bonds

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    NewUrlParser
    -0.54
    itself
    -0.54
     Itself
    -0.53
     itself
    -0.50
    bidities
    -0.49
     detallada
    -0.48
     prossimo
    -0.47
     }}"></
    -0.47
     Route
    -0.46
     arbete
    -0.46
    POSITIVE LOGITS
     SwitchCompat
    0.80
    Personensuche
    0.63
    сылкі
    0.62
    GeneratedMessage
    0.61
    رشف
    0.60
    Diwedd
    0.59
    orianCalendar
    0.59
    TagMode
    0.59
    
    0.58
    IntoConstraints
    0.58
    Activations Density 1.910%

    No Known Activations