© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 51
    Prev
    Next
    INDEX
    Explanations

    references to a character's actions or treatment by others

    oai_token-act-pair · gemini-2.0-flash

    Pronouns and character descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Capitol
    -0.43
    job
    -0.41
     capitol
    -0.40
     gynhyrchwyd
    -0.39
     bead
    -0.39
     kerk
    -0.39
    ве
    -0.38
    Parcelize
    -0.38
     AppCompatTheme
    -0.38
     Ster
    -0.37
    POSITIVE LOGITS
    QMetaType
    0.71
     Monfieur
    0.66
    TagMode
    0.65
    Rhestr
    0.62
     Efq
    0.60
    حياتها
    0.60
    новништво
    0.60
     ProtoMessage
    0.60
     виправивши
    0.57
    ViewImports
    0.57
    Activations Density 4.290%

    No Known Activations