© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4503
    Prev
    Next
    INDEX
    Explanations

    words related to weaponry, combat, and fighting, along with some words related to emotional states

    oai_token-act-pair · gemini-2.0-flash

    Japanese superhero show

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     للمعارف
    -0.99
     ProtoMessage
    -0.80
    tagHelperRunner
    -0.78
    المناصب
    -0.78
    SerializedSize
    -0.77
    TagMode
    -0.76
     nahilalakip
    -0.76
    MessageOf
    -0.75
    ыгана
    -0.75
    RenderAtEndOf
    -0.74
    POSITIVE LOGITS
    AccessorTable
    0.64
     duty
    0.41
    duke
    0.39
     
    0.38
    committees
    0.38
    リュ
    0.37
     D
    0.37
     table
    0.36
     Committees
    0.35
     experts
    0.35
    Activations Density 13.696%

    No Known Activations