© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16298
    Prev
    Next
    INDEX
    Explanations

    uses of the possessive "'s" and articles mentioning "the"

    oai_token-act-pair · gemini-2.0-flash

    s

    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
     its
    -0.62
     his
    -0.60
     a
    -0.56
     seu
    -0.51
    Its
    -0.48
     Its
    -0.48
    C
    -0.47
    B
    -0.46
    and
    -0.46
     sua
    -0.45
    POSITIVE LOGITS
     myſelf
    1.33
     themſelves
    1.27
    ſelf
    1.24
     Majefty
    1.24
     pleaſure
    1.23
     himſelf
    1.22
     purpoſe
    1.20
     greateſt
    1.19
     leaſt
    1.17
     reaſon
    1.16
    Activations Density 22.341%

    No Known Activations