© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13466
    Prev
    Next
    INDEX
    Explanations

    the word "memories" and sometimes words associated with remembering

    oai_token-act-pair · gemini-2.0-flash

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     memories
    -1.05
     memory
    -0.96
    <bos>
    -0.82
    memories
    -0.77
     Memory
    -0.76
    Memory
    -0.74
    memory
    -0.72
     Memories
    -0.67
     memória
    -0.62
     MEMORY
    -0.61
    POSITIVE LOGITS
     становника
    0.74
     pinulongan
    0.68
    styleType
    0.65
    makeConstraints
    0.65
    Personensuche
    0.63
    complexType
    0.63
     المعيارى
    0.62
    ectoria
    0.60
    writeFieldEnd
    0.60
    ⓧ
    0.60
    Activations Density 0.497%

    No Known Activations