© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to basketball

    oai_token-act-pair · gemini-2.0-flash

    basketball

    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
     CURIAM
    -0.69
     Obrador
    -0.66
    ScopeManager
    -0.51
    erráneo
    -0.51
     Waray
    -0.50
    ngdoc
    -0.50
    >{@
    -0.49
     дописавши
    -0.49
    /@
    -0.49
     AssemblyCompany
    -0.49
    POSITIVE LOGITS
     blinding
    0.47
     发表于
    0.47
    expandindo
    0.46
    guien
    0.46
    glGen
    0.44
     StringTokenizer
    0.44
     therewith
    0.43
     estimés
    0.43
    AutoScaleMode
    0.43
    memb
    0.43
    Activations Density 0.399%

    No Known Activations