© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6116
    Prev
    Next
    INDEX
    Explanations

    words related to money or business transactions

    oai_token-act-pair · gemini-2.0-flash

    rare or formal language

    np_max-act · gemini-2.0-flash

    say "word-start" Method used: 2 — tokens mostly start with a word boundary marker — say "word-start"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -1.30
    ↵
    -1.06
    '
    -0.91
    ’
    -0.69
     A
    -0.69
    S
    -0.69
     "
    -0.66
     
    -0.65
    1
    -0.65
     The
    -0.64
    POSITIVE LOGITS
     Majefty
    1.44
     Reſ
    1.35
     Houſe
    1.33
     Anſ
    1.32
     Efq
    1.31
     Diſ
    1.31
     Theſe
    1.31
     myſelf
    1.27
     Monfieur
    1.26
    neſs
    1.24
    Activations Density 36.013%

    No Known Activations