© 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. 916
    Prev
    Next
    INDEX
    Explanations

    the words acre, for and production, and relates to rice and food

    oai_token-act-pair · gemini-2.0-flash

    rice and grains

    np_max-act-logits · 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
     Grain
    -1.55
     grain
    -1.55
    Grain
    -1.52
    grain
    -1.45
     Grains
    -1.33
     grains
    -1.27
     Wheat
    -1.23
     rice
    -1.20
    Rice
    -1.20
     Rice
    -1.19
    POSITIVE LOGITS
    パード
    0.41
    MUM
    0.40
     môi
    0.40
    jstor
    0.38
     webdriver
    0.38
    setdefault
    0.38
    irc
    0.37
    朋
    0.37
    bor
    0.36
     ökolog
    0.35
    Activations Density 1.421%

    No Known Activations