© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4318
    Prev
    Next
    INDEX
    Explanations

    places that are in Thailand.

    oai_token-act-pair · gemini-2.0-flash

    Thailand related

    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
     שוליים
    -0.51
    instancetype
    -0.47
    rigkeit
    -0.42
    كية
    -0.42
     pad
    -0.42
    Looper
    -0.42
    refs
    -0.40
    μέν
    -0.39
    bogen
    -0.39
     structured
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.80
     disambiguazione
    0.77
    NewUrlParser
    0.69
     ExecuteAsync
    0.66
    ]){
    0.66
    uxxxx
    0.65
    "]);
    0.65
    fromnode
    0.63
     Normdatei
    0.62
    ContentAsync
    0.61
    Activations Density 0.352%

    No Known Activations