© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8991
    Prev
    Next
    INDEX
    Explanations

    code snippets in various languages likely to define boolean logic

    oai_token-act-pair · gemini-2.0-flash

    =

    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
    false
    -1.68
    true
    -1.63
     false
    -1.63
     null
    -1.52
     true
    -1.50
    null
    -1.49
     nullptr
    -1.02
    nullptr
    -0.91
     untrue
    -0.84
     falso
    -0.81
    POSITIVE LOGITS
     duchess
    0.44
    inaison
    0.44
     digress
    0.43
    zaak
    0.41
    IGATION
    0.41
     showers
    0.41
    apyrus
    0.41
    นู
    0.40
    award
    0.40
     contemporaries
    0.40
    Activations Density 6.929%

    No Known Activations