© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7986
    Prev
    Next
    INDEX
    Explanations

    words relating to places, things, people and activities such as buying, or places such as Arsenal.

    oai_token-act-pair · gemini-2.0-flash

    Mate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    djangoproject
    -0.64
    amssymb
    -0.57
    出版年
    -0.54
     CURIAM
    -0.51
    SerializedName
    -0.51
     cứ
    -0.50
     دیکھیے
    -0.49
    ამ
    -0.49
    tiko
    -0.49
    例句
    -0.48
    POSITIVE LOGITS
     mate
    1.87
     mates
    1.57
     loads
    1.45
     Loads
    1.40
     load
    1.38
    Loads
    1.23
     Mate
    1.21
     MATE
    1.17
    Mate
    1.16
    load
    1.15
    Activations Density 2.935%

    No Known Activations