© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5378
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words associated with personal connection and reference.

    oai_token-act-pair · gemini-2.0-flash

    their

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     their
    -2.14
    Their
    -1.84
    their
    -1.84
     Their
    -1.78
     THEIR
    -1.38
     leurs
    -1.36
     kanilang
    -1.34
     leur
    -1.28
     themselves
    -1.24
     loro
    -1.20
    POSITIVE LOGITS
     onAnimation
    0.57
    umą
    0.51
    SBATCH
    0.51
     élevées
    0.51
     étrangères
    0.49
    countries
    0.48
     heretics
    0.47
    setopt
    0.47
     doméstico
    0.47
    steroids
    0.47
    Activations Density 7.468%

    No Known Activations