© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13760
    Prev
    Next
    INDEX
    Explanations

    references to time and causality, often including words or phrases like "before", "when", "if", or "or".

    oai_token-act-pair · gemini-2.0-flash

    before

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    migrationBuilder
    -0.85
    脚注の使い方
    -0.82
    EndProject
    -0.75
    TypedDataSet
    -0.75
    MENAFN
    -0.66
    Дереккөздер
    -0.65
    Autoritní
    -0.65
     חיצוניים
    -0.65
    protoimpl
    -0.63
    Tikang
    -0.62
    POSITIVE LOGITS
    TagMode
    0.52
    work
    0.51
     Hanley
    0.49
     disadvantages
    0.48
     development
    0.48
     squatting
    0.48
     organizing
    0.48
    working
    0.47
     work
    0.47
     working
    0.47
    Activations Density 11.436%

    No Known Activations