© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    references to American football players and teams

    oai_token-act-pair · gemini-2.0-flash

    sports positions

    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
     '\\;'
    -0.61
    Skocz
    -0.59
    خة
    -0.57
    makeConstraints
    -0.55
     InputDecoration
    -0.55
     balsam
    -0.55
    MatButtonModule
    -0.54
    ActivityCompat
    -0.54
     disambiguazione
    -0.54
    BagConstraints
    -0.54
    POSITIVE LOGITS
     free
    0.44
    ショナル
    0.43
     commandés
    0.43
     numberOfRows
    0.43
     untersch
    0.42
    commod
    0.41
    föra
    0.40
    ڑ
    0.40
    Portale
    0.40
     estimés
    0.40
    Activations Density 0.420%

    No Known Activations