© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4874
    Prev
    Next
    INDEX
    Explanations

    words related to historical expeditions, military actions, travel, and people's titles.

    oai_token-act-pair · gemini-2.0-flash

    expeditions and trips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ########.
    -0.51
    phazard
    -0.43
    uxley
    -0.43
    conos
    -0.42
    inta
    -0.42
    ("$.
    -0.41
     Remote
    -0.40
     Piaget
    -0.39
    APORE
    -0.39
    Remote
    -0.39
    POSITIVE LOGITS
     purpoſe
    0.83
    SequentialGroup
    0.80
     pleaſure
    0.77
     doInBackground
    0.69
    InputBorder
    0.68
     myſelf
    0.68
    WebVitals
    0.67
     RIPRODUZIONE
    0.66
    Tembelea
    0.66
     समीक्षाओं
    0.65
    Activations Density 2.388%

    No Known Activations