© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6738
    Prev
    Next
    INDEX
    Explanations

    numerical data, with a preference for numbers formatted in a source code context or large numbers presented in a context of potentially false information

    oai_token-act-pair · gemini-2.0-flash

    numeric representations and related terms

    np_token-act-pair-logits · gpt-4o-mini

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    cetype
    -0.54
     tartalomajánló
    -0.53
    "){
    -0.53
    ialog
    -0.52
     ),
    -0.52
    )}
    -0.50
    enterOuterAlt
    -0.50
     "")
    -0.50
      (
    -0.50
     straips
    -0.50
    POSITIVE LOGITS
    0
    1.14
    awtextra
    0.71
    ০
    0.67
     defaultstate
    0.65
    ۰
    0.63
    ０
    0.63
     esternos
    0.62
     للمعارف
    0.62
    𝟎
    0.59
    ٠
    0.59
    Activations Density 4.414%

    No Known Activations