© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3354
    Prev
    Next
    INDEX
    Explanations

    a specific person's name "Kaamilya", and also finds some data packets.

    oai_token-act-pair · 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
     Mosley
    -0.61
     Vitale
    -0.57
     RAC
    -0.56
     Boucher
    -0.54
     Kram
    -0.50
    Packet
    -0.49
    pani
    -0.49
     Cara
    -0.49
     Caron
    -0.49
    unay
    -0.48
    POSITIVE LOGITS
    __':
    0.88
    SharedCtor
    0.86
     Мексичка
    0.85
    Personensuche
    0.79
    fillType
    0.77
    __":
    0.77
    AddTagHelper
    0.76
     مرئيه
    0.75
     الحره
    0.75
    contentLoaded
    0.75
    Activations Density 7.773%

    No Known Activations