Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14423
    Prev
    Next
    INDEX
    Explanations

    medical terminology especially related to spinal injuries

    oai_token-act-pair · gemini-2.0-flash

    spinal

    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
     незавершена
    -1.03
    tvguidetime
    -0.93
     utafitiHapana
    -0.85
    GEBURTSDATUM
    -0.81
    GraphicsUnit
    -0.80
    ToBounds
    -0.74
    sidemargin
    -0.73
     ProtoMessage
    -0.73
    AccessorTable
    -0.72
    MemoryWarning
    -0.71
    POSITIVE LOGITS
     back
    0.92
    back
    0.78
     Back
    0.73
    Back
    0.72
     BACK
    0.69
    BACK
    0.68
     backs
    0.64
     L
    0.60
    backs
    0.57
    バック
    0.56
    Activations Density 1.061%

    No Known Activations