© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12158
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions, beliefs, and observations

    oai_token-act-pair · gemini-2.0-flash

    I or we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     my
    -1.09
     our
    -1.02
    my
    -0.93
     mine
    -0.86
     meine
    -0.83
     nuestros
    -0.82
     minha
    -0.81
    我的
    -0.81
     meus
    -0.81
    Our
    -0.80
    POSITIVE LOGITS
     I
    1.13
     we
    1.02
     я
    0.84
     We
    0.84
    medriver
    0.77
    We
    0.75
    we
    0.74
     ExecuteAsync
    0.70
    I
    0.69
    XmlAccessorType
    0.68
    Activations Density 3.532%

    No Known Activations