© 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
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 12071
    Prev
    Next
    INDEX
    Explanations

    mentions of body measurements, medical results, and other health-related information, particularly in the context of test results, symptoms and the phrase "i herd thet".

    oai_token-act-pair · gemini-2.0-flash

    ing

    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
    NUMX
    -0.89
    )":
    -0.88
    Билгалдахарш
    -0.86
    contentLoaded
    -0.81
    "):
    
    -0.80
     Paglinawan
    -0.80
    )':
    -0.79
    )")
    -0.79
    IsMutable
    -0.76
    ')")
    -0.76
    POSITIVE LOGITS
      
    0.69
    (
    0.57
    祥
    0.56
     didalam
    0.54
     disini
    0.51
     to
    0.49
    .....
    0.49
    何故
    0.49
     and
    0.49
     Thomas
    0.49
    Activations Density 0.740%

    No Known Activations