© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9285
    Prev
    Next
    INDEX
    Explanations

    mentions of 'analytics', HTML paragraph tags, medical topics related to eyes, and political titles

    oai_token-act-pair · gemini-2.0-flash

    Data analytics and eye health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Parcelize
    -0.73
    styleType
    -0.70
    BeginContext
    -0.68
    >({
    -0.67
     makeStyles
    -0.67
     useStyles
    -0.64
    }}],
    -0.63
    findpost
    -0.61
     ControllerBase
    -0.60
     Hän
    -0.60
    POSITIVE LOGITS
    addPreferredGap
    0.64
     indisponible
    0.61
    Rujuakan
    0.58
    出版年
    0.56
    CrossRef
    0.56
    GIVEREF
    0.54
    bihan
    0.52
     mukana
    0.49
     خیر
    0.49
     defStyleAttr
    0.48
    Activations Density 1.192%

    No Known Activations