© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1874
    Prev
    Next
    INDEX
    Explanations

    terms relating to illnesses, particularly mental or vision-related.

    oai_token-act-pair · gemini-2.0-flash

    medical conditions, studies

    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
     protoimpl
    -0.66
    OGND
    -0.63
     MainAxisSize
    -0.55
    maketitle
    -0.54
    Hozzáférés
    -0.52
    expandindo
    -0.52
     levier
    -0.50
     onView
    -0.48
    GraphicsUnit
    -0.47
     Barriers
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.58
     EconPapers
    0.56
    ându
    0.56
     Commencez
    0.55
    Tikang
    0.50
    URRED
    0.50
    Publication
    0.50
    Билгалдахарш
    0.48
    aarrggbb
    0.48
    peda
    0.47
    Activations Density 2.991%

    No Known Activations