© 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. 16268
    Prev
    Next
    INDEX
    Explanations

    words related to physical exercise

    oai_token-act-pair · gemini-2.0-flash

    Scientific/Academic text

    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
    ftagPool
    -0.85
    rrggbb
    -0.83
    SerializedSize
    -0.80
    currentColor
    -0.71
    ClientRect
    -0.69
     unknownFields
    -0.67
    train
    -0.66
    principalColumn
    -0.65
     train
    -0.63
     AssemblyCompany
    -0.63
    POSITIVE LOGITS
     trå
    0.49
     Fä
    0.47
    XmlAccessType
    0.46
     cricket
    0.45
    wana
    0.44
     möge
    0.43
     MonoBehaviour
    0.41
    ньому
    0.41
     pierre
    0.40
     fă
    0.40
    Activations Density 5.737%

    No Known Activations