© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11201
    Prev
    Next
    INDEX
    Explanations

    language related to injuries in sports

    oai_token-act-pair · gemini-2.0-flash

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     мәкал
    -0.65
    ciaż
    -0.64
     CURIAM
    -0.60
     saites
    -0.54
    ADATA
    -0.52
    "]),
    -0.51
    HasAnnotation
    -0.50
    améli
    -0.50
    GEBURTS
    -0.49
    '">
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.63
    GenerationType
    0.62
    ьаж
    0.62
     GlobalKey
    0.60
    ArrowToggle
    0.55
    ArgsConstructor
    0.54
    InteropServices
    0.53
    ServletException
    0.52
     Affiliations
    0.51
     Sabha
    0.50
    Activations Density 0.491%

    No Known Activations