© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7485
    Prev
    Next
    INDEX
    Explanations

    mentions of health or population studies, especially those conducted by the CDC

    oai_token-act-pair · gemini-2.0-flash

    study/report

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -0.98
     Theſe
    -0.92
     pinulongan
    -0.89
     дописавши
    -0.85
    OGND
    -0.83
     ―――――
    -0.81
    HasAnnotation
    -0.80
     myſelf
    -0.79
     snippetHide
    -0.77
     purpoſe
    -0.77
    POSITIVE LOGITS
     tindak
    0.48
    Model
    0.45
    ocera
    0.44
     cui
    0.40
     Covid
    0.40
     bowiem
    0.40
    ².
    0.40
     hver
    0.40
     ou
    0.39
     C
    0.39
    Activations Density 2.478%

    No Known Activations