© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    words in the context of law, taxes, and debt

    oai_token-act-pair · gemini-2.0-flash

    Code and quotes

    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
     “
    -3.36
    “
    -2.98
    ”
    -2.86
    ’”
    -2.63
    ”.
    -2.53
    ”,
    -2.53
    ，“
    -2.48
    ,”
    -2.44
    .”
    -2.36
    ”)
    -2.33
    POSITIVE LOGITS
    €¦
    0.56
     {@
    0.50
    BeginContext
    0.50
    MLLoader
    0.43
     <?=
    0.41
    {@
    0.38
    ftagPool
    0.38
    MenuInflater
    0.38
    ोड़
    0.36
     autorytatywna
    0.36
    Activations Density 32.879%

    No Known Activations