© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14641
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and words associated with them.

    oai_token-act-pair · gemini-2.0-flash

    wellbeing

    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
    تقاوى
    -0.76
     AssemblyCulture
    -0.71
    windowFixed
    -0.68
    parsedMessage
    -0.63
     Reverso
    -0.60
    PrototypeOf
    -0.57
    Географи
    -0.56
    XmlAccessType
    -0.54
    endregion
    -0.53
    principalColumn
    -0.53
    POSITIVE LOGITS
     health
    1.55
     safety
    1.43
     welfare
    1.35
    health
    1.25
    safety
    1.20
     wellbeing
    1.20
     sanity
    1.16
     sustainability
    1.09
     wellness
    1.05
     survival
    1.05
    Activations Density 4.177%

    No Known Activations