© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5693
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, particularly college sports with named universities

    oai_token-act-pair · gemini-2.0-flash

    sports news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UserScript
    -0.63
     ostavi
    -0.55
    rantz
    -0.50
    fhir
    -0.49
     Cristóbal
    -0.49
    AsUp
    -0.48
    noopener
    -0.48
    kháu
    -0.48
    perma
    -0.47
    物
    -0.46
    POSITIVE LOGITS
    httphttps
    0.63
     فريبيس
    0.62
     विश्वसनीयता
    0.61
    ########.
    0.56
     Normdatei
    0.55
     setContent
    0.53
    '),
    0.53
     Pitt
    0.53
    resultCode
    0.52
    enterian
    0.51
    Activations Density 0.904%

    No Known Activations