© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6365
    Prev
    Next
    INDEX
    Explanations

    language related to recovery and medical situations or procedures, and also to athletic training.

    oai_token-act-pair · gemini-2.0-flash

    working

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SHOT
    -0.52
     NUKAT
    -0.51
     SHOT
    -0.50
    Shot
    -0.49
    nessy
    -0.47
     masak
    -0.47
     Glaser
    -0.46
     shot
    -0.45
     Shot
    -0.45
    ymce
    -0.45
    POSITIVE LOGITS
     workforce
    0.71
     working
    0.71
    working
    0.68
     ModelExpression
    0.67
     Working
    0.65
     WORKING
    0.65
    WORKING
    0.64
    Working
    0.63
     return
    0.63
     Rb
    0.62
    Activations Density 0.954%

    No Known Activations