© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13367
    Prev
    Next
    INDEX
    Explanations

    soccer-related text

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming references

    np_token-act-pair-logits · gpt-4o-mini

    Sports leagues and cups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     الحره
    -0.81
    脚注の使い方
    -0.60
     للمعارف
    -0.58
    Havolalar
    -0.58
    Personendaten
    -0.57
    windowFixed
    -0.56
     kaarangay
    -0.56
    nlm
    -0.56
     calendriers
    -0.56
     صوتيه
    -0.55
    POSITIVE LOGITS
    PickerController
    0.66
    stretchr
    0.56
    ollectionView
    0.54
    exels
    0.54
    PageFactory
    0.52
    octet
    0.49
    ARIUS
    0.49
    GroupLayout
    0.49
     catch
    0.49
    kuuta
    0.48
    Activations Density 0.462%

    No Known Activations