© 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. 12268
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and experiments in academic papers

    oai_token-act-pair · gemini-2.0-flash

    Figure

    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
     EconPapers
    -0.73
    stateProvider
    -0.61
     neceff
    -0.60
     auffi
    -0.59
     OFDb
    -0.58
     fevere
    -0.57
    зулта
    -0.56
    Geplaatst
    -0.56
     Commencez
    -0.55
     Meksiku
    -0.55
    POSITIVE LOGITS
     S
    0.68
     AI
    0.68
     A
    0.65
     AR
    0.63
     B
    0.57
     AV
    0.57
     N
    0.56
     D
    0.56
     SA
    0.55
     Sa
    0.54
    Activations Density 15.397%

    No Known Activations