© 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. 10383
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and royalty

    oai_token-act-pair · gemini-2.0-flash

    Historical contexts

    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
     lenker
    -0.56
    Identification
    -0.54
    ULATOR
    -0.54
    InvalidProtocol
    -0.52
     Identify
    -0.52
     Identifying
    -0.52
     gra
    -0.51
    TO
    -0.51
     identifying
    -0.50
     Identification
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.74
    ſelves
    0.65
    -------------</
    0.64
     Anſ
    0.63
     الحره
    0.63
     hâte
    0.62
    脚注の使い方
    0.62
     ―――――
    0.62
     larmes
    0.61
    jalá
    0.61
    Activations Density 1.849%

    No Known Activations