© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16186
    Prev
    Next
    INDEX
    Explanations

    mentions of statistics, studies, history, legal proceedings, and similar things.

    oai_token-act-pair · 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
     StatefulWidget
    -0.70
     ویکی‌پدیای
    -0.60
    脚注の使い方
    -0.59
     ſtate
    -0.53
     pleaſure
    -0.53
     nargin
    -0.52
     purpoſe
    -0.51
     UIFont
    -0.50
     IBOutlet
    -0.49
     cauſe
    -0.48
    POSITIVE LOGITS
     starting
    2.80
    starting
    2.47
     Starting
    2.41
    Starting
    2.38
     beginning
    2.34
    beginning
    2.08
     STARTING
    2.02
    Beginning
    1.97
     Beginning
    1.92
    STARTING
    1.77
    Activations Density 15.208%

    No Known Activations