© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7913
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and associated phrases

    oai_token-act-pair · gemini-2.0-flash

    I, we, they

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mourut
    -0.70
     heals
    -0.64
     washes
    -0.64
    Knows
    -0.63
    Enjoyed
    -0.62
     plays
    -0.57
    提供了
    -0.57
     hoort
    -0.57
     hebt
    -0.56
     impianti
    -0.56
    POSITIVE LOGITS
     take
    1.06
     make
    1.03
     communicate
    0.99
     raise
    0.99
     declare
    0.94
     generate
    0.93
     operate
    0.92
     integrate
    0.92
     bring
    0.92
     have
    0.92
    Activations Density 2.374%

    No Known Activations