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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14146
    Prev
    Next
    INDEX
    Explanations

    the word "last", sometimes preceded by "the" or followed by "week" or "year", and to a lesser extent "next"

    oai_token-act-pair · gemini-2.0-flash

    last

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    DialogResult
    -0.45
     hadapan
    -0.45
     bont
    -0.43
    ఠ
    -0.43
     Putih
    -0.42
    ρων
    -0.40
    minyak
    -0.40
    zondere
    -0.39
    manera
    -0.39
     Strahl
    -0.38
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
     protoimpl
    0.78
     EconPapers
    0.72
     InputDecoration
    0.70
    Tracce
    0.69
    principalTable
    0.67
    addPreferredGap
    0.66
    addGap
    0.66
    TagMode
    0.65
    abestanden
    0.64
    Activations Density 1.165%

    No Known Activations