© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political events, actions, and individuals within an organizational structure.

    oai_token-act-pair · gemini-2.0-flash

    Politics and resignations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     himſelf
    -0.93
    AndEndTag
    -0.90
     myſelf
    -0.85
     himself
    -0.84
     itſelf
    -0.80
     transfieras
    -0.78
    himself
    -0.77
     незавершена
    -0.77
    IndentedString
    -0.74
     herself
    -0.73
    POSITIVE LOGITS
     We
    0.54
     our
    0.54
     ourselves
    0.48
     collective
    0.48
     saling
    0.46
     Our
    0.46
    rupa
    0.46
     själva
    0.44
    みんなで
    0.43
     نحن
    0.43
    Activations Density 6.154%

    No Known Activations