© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12714
    Prev
    Next
    INDEX
    Explanations

    words contrasting internal and external things

    oai_token-act-pair · gemini-2.0-flash

    external

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     external
    -1.15
    External
    -1.05
     External
    -1.05
     ekster
    -1.03
     externally
    -1.02
     Extern
    -1.01
    external
    -0.99
     EXTERNAL
    -0.98
     externe
    -0.98
     outside
    -0.97
    POSITIVE LOGITS
    務省
    0.51
     незавершена
    0.50
    primaryStage
    0.50
    act
    0.50
    servez
    0.49
    Демографія
    0.48
    usermodel
    0.48
    uxxxx
    0.47
    niczy
    0.47
    ]^{-
    0.46
    Activations Density 14.686%

    No Known Activations