© 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. 2261
    Prev
    Next
    INDEX
    Explanations

    code and programming related terms

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act-logits · gemini-2.0-flash

    say "endings like -ess/-ation"

    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_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
     ExecuteAsync
    -0.48
     pageContext
    -0.41
    assies
    -0.37
    wesenheit
    -0.37
    leih
    -0.36
    middels
    -0.35
     IDL
    -0.35
    Джерела
    -0.35
    styleType
    -0.34
     démission
    -0.34
    POSITIVE LOGITS
    ]--;
    0.59
     houſe
    0.50
     tranſ
    0.49
     ſtate
    0.49
     purpoſe
    0.48
     "\""
    0.48
    før
    0.48
    dyti
    0.48
     {}),
    0.48
    gående
    0.48
    Activations Density 5.692%

    No Known Activations