© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7360
    Prev
    Next
    INDEX
    Explanations

    tokens appearing in code, URLs, and categories related to sports and football players

    oai_token-act-pair · gemini-2.0-flash

    technical and foreign language

    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
     da
    -0.44
    Heating
    -0.41
     serca
    -0.40
     ДЛЯ
    -0.40
    nommen
    -0.40
     ochrony
    -0.40
     liście
    -0.39
     Circulation
    -0.39
     miejscowości
    -0.39
    ɵɵ
    -0.39
    POSITIVE LOGITS
     raiſ
    0.73
     kasarigan
    0.70
     houſe
    0.67
    mybatisplus
    0.66
    CPtr
    0.66
     Efq
    0.66
     ſmall
    0.65
     faſt
    0.65
    +#+
    0.64
     pinulongan
    0.64
    Activations Density 0.369%

    No Known Activations