© 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. 5275
    Prev
    Next
    INDEX
    Explanations

    number and shape adjectives used in science and math articles

    oai_token-act-pair · gemini-2.0-flash

    multidimensional system

    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
    uvres
    -0.61
    ьаж
    -0.61
     intptr
    -0.59
    openhague
    -0.58
    fois
    -0.58
    ftances
    -0.58
    MigrationBuilder
    -0.57
     plufieurs
    -0.57
     別注
    -0.56
    dirond
    -0.56
    POSITIVE LOGITS
     propOrder
    0.66
    ᴗ
    0.45
    alt
    0.44
    delegate
    0.43
     gynhyrchwyd
    0.43
     ste
    0.42
     Higgs
    0.40
     departament
    0.39
     order
    0.38
    SpringRunner
    0.38
    Activations Density 11.468%

    No Known Activations