© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11460
    Prev
    Next
    INDEX
    Explanations

    words and sequences related to genetics and protein mutations

    oai_token-act-pair · gemini-2.0-flash

    Amino acid mutations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     '\\;'
    -0.99
    ChildScrollView
    -0.97
    Personensuche
    -0.77
     BoxFit
    -0.76
    bibitem
    -0.72
    IUrlHelper
    -0.72
    AnimationsModule
    -0.71
    
    -0.71
     useAppContext
    -0.69
    Bibliographie
    -0.67
    POSITIVE LOGITS
     integra
    0.49
    int
    0.48
    S
    0.46
     or
    0.45
    ionine
    0.45
     ani
    0.45
    for
    0.44
    egli
    0.43
    дени
    0.43
    AutoField
    0.43
    Activations Density 1.769%

    No Known Activations