© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12283
    Prev
    Next
    INDEX
    Explanations

    words related to the description and diagnosis of medical, psychiatric, and behavioral conditions.

    oai_token-act-pair · gemini-2.0-flash

    Medical signs or symptoms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    idate
    -0.64
    omethane
    -0.60
    Hochspringen
    -0.57
    دانشنامهٔ
    -0.56
    abestanden
    -0.55
    visation
    -0.55
    Viitteet
    -0.55
    ollectionView
    -0.55
    UniformLocation
    -0.52
     Forth
    -0.51
    POSITIVE LOGITS
    <bos>
    0.85
     characteristic
    0.58
     caractéristique
    0.57
    characteristic
    0.56
    ellemző
    0.56
     characteristics
    0.55
    function
    0.54
    FEATURE
    0.54
    \{\\
    0.54
     features
    0.53
    Activations Density 1.772%

    No Known Activations