© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2664
    Prev
    Next
    INDEX
    Explanations

    words related to sports team injuries and games

    oai_token-act-pair · gemini-2.0-flash

    basketball teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     NBA
    -0.65
     NHL
    -0.64
    dataclass
    -0.63
     незавершена
    -0.61
     NFL
    -0.59
    protoimpl
    -0.56
    Demografia
    -0.55
    RTEX
    -0.55
     DCM
    -0.55
    MatInputModule
    -0.54
    POSITIVE LOGITS
    SourceChecksum
    0.53
     MonoBehaviour
    0.46
    WebVitals
    0.45
     Timber
    0.43
    pement
    0.43
    Timber
    0.43
     poche
    0.43
    spo
    0.42
    चे
    0.42
    ória
    0.42
    Activations Density 1.998%

    No Known Activations