© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     I
    -0.84
    I
    -0.75
     i
    -0.47
     я
    -0.45
     after
    -0.45
    我不
    -0.44
    Ｉ
    -0.44
     đ
    -0.43
     tkinter
    -0.43
    rc
    -0.42
    POSITIVE LOGITS
    <bos>
    1.30
     itſelf
    0.91
     Efq
    0.90
     Monfieur
    0.85
    ſelves
    0.85
     Shakspeare
    0.85
     Jefus
    0.84
    ſelf
    0.82
     myſelf
    0.82
     Theſe
    0.81
    Activations Density 1.817%

    No Known Activations