© 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. 4602
    Prev
    Next
    INDEX
    Explanations

    patients or medical workers providing or receiving treatment.

    oai_token-act-pair · gemini-2.0-flash

    medical contexts

    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
    migrationBuilder
    -0.84
    SequentialGroup
    -0.83
    awtextra
    -0.73
    esModule
    -0.73
    ագրություններ
    -0.70
    windowFixed
    -0.69
     "..\..\..\
    -0.68
     oprot
    -0.67
     SwitchCompat
    -0.67
    Portály
    -0.66
    POSITIVE LOGITS
    liau
    0.47
     received
    0.44
     sought
    0.43
     buscan
    0.43
    n
    0.42
     receive
    0.41
     seek
    0.40
    ween
    0.40
     Received
    0.40
     الرياضيه
    0.39
    Activations Density 2.213%

    No Known Activations