© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6101
    Prev
    Next
    INDEX
    Explanations

    words related to politics and geography

    oai_token-act-pair · gemini-2.0-flash

    earlier

    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
     myſelf
    -0.88
     himſelf
    -0.79
    IsContent
    -0.79
    ValueStyle
    -0.78
     ſhe
    -0.77
     itſelf
    -0.76
     poffe
    -0.75
     themſelves
    -0.75
     Efq
    -0.75
     Monfieur
    -0.73
    POSITIVE LOGITS
     earlier
    1.68
     Earlier
    1.65
    earlier
    1.59
    Earlier
    1.57
     EARL
    0.91
     wcześniej
    0.70
     tadi
    0.62
     India
    0.60
     later
    0.59
     eerder
    0.59
    Activations Density 2.046%

    No Known Activations