© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9743
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs related to people frequently mentioned within a text

    oai_token-act-pair · gemini-2.0-flash

    future tense

    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
     won
    -0.94
    将
    -0.90
    將
    -0.83
    will
    -0.81
     Won
    -0.81
     werden
    -0.79
    Won
    -0.79
    won
    -0.79
     Will
    -0.75
     wont
    -0.73
    POSITIVE LOGITS
     GenerationType
    0.94
    GraphicsUnit
    0.88
     تضيفلها
    0.85
    ########.
    0.84
    SharedCtor
    0.82
     متعلقه
    0.81
    tvguidetime
    0.78
     photolibrary
    0.77
     الرياضيه
    0.76
     autorytatywna
    0.75
    Activations Density 0.582%

    No Known Activations