© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12020
    Prev
    Next
    INDEX
    Explanations

    mentions of weather, especially severe weather

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming concepts

    np_token-act-pair-logits · gpt-4o-mini

    Weather events and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    shmi
    -0.42
     fís
    -0.42
     bodily
    -0.41
    يع
    -0.39
     صوتيه
    -0.39
    instagram
    -0.39
     ducha
    -0.38
    Instagram
    -0.38
    пев
    -0.38
    ficação
    -0.37
    POSITIVE LOGITS
    +#+#
    0.84
     propOrder
    0.79
    AddTagHelper
    0.74
    DoubleQuotes
    0.70
    scrapy
    0.68
    tagHelperRunner
    0.66
    HideFlags
    0.66
    ThroughAttribute
    0.65
    valdi
    0.64
    mphony
    0.64
    Activations Density 0.597%

    No Known Activations