© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11296
    Prev
    Next
    INDEX
    Explanations

    strings of words related to medical studies involving patients with a specific condition

    oai_token-act-pair · gemini-2.0-flash

    Medical studies/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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     chré
    -0.60
     âgées
    -0.60
     actuels
    -0.57
     igång
    -0.55
     scuro
    -0.55
     scolaires
    -0.55
     gratuits
    -0.54
    ագրություններ
    -0.54
     sauvages
    -0.54
     naturelles
    -0.52
    POSITIVE LOGITS
     InputDecoration
    0.66
     DialogInterface
    0.58
    JNIEnv
    0.56
    CopyWith
    0.55
    outState
    0.54
    SequentialGroup
    0.53
    FormTagHelper
    0.52
    Архівовано
    0.52
    KEYCODE
    0.51
    onViewCreated
    0.51
    Activations Density 2.977%

    No Known Activations