© 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. 5087
    Prev
    Next
    INDEX
    Explanations

    chemistry or biochemistry related terminology or notation

    oai_token-act-pair · gemini-2.0-flash

    chemical/scientific texts

    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
    aarrggbb
    -0.68
     Ex
    -0.63
     EX
    -0.62
    eX
    -0.61
     Phry
    -0.60
     uVar
    -0.59
     cx
    -0.58
    Ex
    -0.57
    EX
    -0.56
    TestingModule
    -0.55
    POSITIVE LOGITS
    ks
    0.84
    KS
    0.66
    ksy
    0.65
    Portale
    0.60
    ksu
    0.56
     uska
    0.54
    ksis
    0.53
    ಕ್
    0.53
    kso
    0.52
     ks
    0.51
    Activations Density 1.584%

    No Known Activations