© 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. 13485
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns or adjectives describing people

    oai_token-act-pair · gemini-2.0-flash

    Possessions/Relationships

    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
    ViewFeatures
    -0.56
     LayoutInflater
    -0.54
     Jun
    -0.49
    PropertyChanging
    -0.49
    euvres
    -0.49
    GOTREF
    -0.48
    individuals
    -0.48
    Rujukan
    -0.48
     Sep
    -0.48
     onto
    -0.48
    POSITIVE LOGITS
     Chriftian
    0.79
    WEBPACK
    0.62
     Moslem
    0.59
     chrétien
    0.59
    lankton
    0.59
     Efq
    0.57
     Shakspeare
    0.57
     ſeveral
    0.56
    balleur
    0.55
    참고
    0.53
    Activations Density 1.125%

    No Known Activations