© 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. 5173
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words that lead to them such as "introducing us" or "join us"

    oai_token-act-pair · gemini-2.0-flash

    say "us"

    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
     we
    -3.20
    We
    -2.23
     We
    -2.08
     мы
    -1.90
    we
    -1.90
    我們
    -1.76
    我们
    -1.75
     nous
    -1.73
    Мы
    -1.53
     我们
    -1.45
    POSITIVE LOGITS
     uns
    0.64
    canestro
    0.58
    ेशा
    0.55
    TagMode
    0.54
    ükemmel
    0.51
    Uns
    0.51
    LikeLike
    0.51
     referenties
    0.50
    ExtendWith
    0.50
     препратки
    0.50
    Activations Density 5.665%

    No Known Activations