© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11443
    Prev
    Next
    INDEX
    Explanations

    words related to cooking or recipes

    oai_token-act-pair · gemini-2.0-flash

    program

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Personendaten
    -0.88
    UserScript
    -0.86
     Jefus
    -0.84
     Pingback
    -0.79
     NgModule
    -0.78
    awtextra
    -0.77
    iastes
    -0.77
    enumi
    -0.77
    IsContent
    -0.74
    EDEFAULT
    -0.74
    POSITIVE LOGITS
     program
    0.70
    program
    0.64
     Program
    0.61
     программе
    0.60
    programs
    0.60
     programa
    0.59
    Program
    0.58
    Programm
    0.57
    programm
    0.57
     programs
    0.56
    Activations Density 0.613%

    No Known Activations