© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10995
    Prev
    Next
    INDEX
    Explanations

    words related to sounds from or descriptions of disturbances or sounds in an apartment

    oai_token-act-pair · gemini-2.0-flash

    Loud sounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    цездатний
    -0.52
    Erreferentziak
    -0.51
    المشاركات
    -0.50
    makeText
    -0.48
    сылкі
    -0.47
    msgTypes
    -0.46
     energética
    -0.45
     traite
    -0.44
    '])){
    -0.43
    청
    -0.43
    POSITIVE LOGITS
    protoimpl
    0.72
     protoimpl
    0.68
    Хьажоргаш
    0.67
    ImageContext
    0.56
    zember
    0.56
    日閲覧
    0.53
    RUnlock
    0.52
     propOrder
    0.52
    Diwedd
    0.52
    
    0.51
    Activations Density 0.629%

    No Known Activations