© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4504
    Prev
    Next
    INDEX
    Explanations

    descriptions of Thai restaurants and food

    oai_token-act-pair · gemini-2.0-flash

    shopping locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     fe
    -0.43
    ence
    -0.41
    AddHtmlAttribute
    -0.40
     character
    -0.40
     menyal
    -0.39
    ecma
    -0.38
    ribusi
    -0.38
    Imp
    -0.38
    VIATIONS
    -0.38
     conmigo
    -0.37
    POSITIVE LOGITS
     صوتيه
    0.85
    SharedCtor
    0.81
    Autoritní
    0.81
     الحره
    0.72
    
    0.71
     Normdatei
    0.70
    saraba
    0.69
     يتيمه
    0.69
    MigrationBuilder
    0.68
     متعلقه
    0.67
    Activations Density 19.375%

    No Known Activations