© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10544
    Prev
    Next
    INDEX
    Explanations

    what appears to be phrases from machine-translated Chinese dealing with violence and possibly martial arts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CURIAM
    -0.63
     kasarigan
    -0.59
     ModelExpression
    -0.54
     quý
    -0.52
     bú
    -0.50
    \}^{
    -0.49
    Reach
    -0.48
    jfree
    -0.48
     Hat
    -0.46
    addCriterion
    -0.46
    POSITIVE LOGITS
     MainAxisSize
    0.77
    脚注の使い方
    0.61
     itſelf
    0.58
     Pergamon
    0.58
    CloseOperation
    0.57
    ENODEV
    0.55
     Carni
    0.53
     MessageBoxIcon
    0.53
     Kuru
    0.52
     Managua
    0.51
    Activations Density 0.415%

    No Known Activations