© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13245
    Prev
    Next
    INDEX
    Explanations

    the names, descriptions, and reviews of Indian restaurants in Kuala Lumpur

    oai_token-act-pair · gemini-2.0-flash

    Indian food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    roek
    -0.58
     COMMENTS
    -0.56
    resos
    -0.56
     Generales
    -0.56
    Étymologie
    -0.56
    brite
    -0.56
     poffe
    -0.54
    extField
    -0.54
     Escribe
    -0.54
     годов
    -0.53
    POSITIVE LOGITS
     resourceCulture
    0.63
     <<<<<<<<<<<<<<
    0.53
    GEBURTSDATUM
    0.50
     th
    0.49
    principalTable
    0.47
     Th
    0.47
    Portail
    0.46
    RTEE
    0.45
    MemoryWarning
    0.45
    FailureListener
    0.44
    Activations Density 1.381%

    No Known Activations