© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11224
    Prev
    Next
    INDEX
    Explanations

    language used in medical reports, particularly symptoms, diagnoses, and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    medical conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ChildScrollView
    -0.68
    PyExc
    -0.65
     newBuilder
    -0.62
    ProgressHUD
    -0.60
     smtplib
    -0.60
    GOTREF
    -0.60
     дописавши
    -0.59
     ISNI
    -0.59
    kháu
    -0.59
    ntomas
    -0.59
    POSITIVE LOGITS
    ühner
    0.49
    break
    0.49
     MainAxisSize
    0.48
    BoxShadow
    0.48
    Jadi
    0.47
    unsqueeze
    0.47
     pleaſure
    0.47
    Split
    0.47
    volen
    0.44
    ity
    0.44
    Activations Density 8.084%

    No Known Activations