© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 174
    Prev
    Next
    INDEX
    Explanations

    language related to the farming of rice and agricultural policy

    oai_token-act-pair · gemini-2.0-flash

    agriculture, farming, food production

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tdessen
    -0.63
     utafitiHapana
    -0.62
    +#+
    -0.62
     Roskov
    -0.60
     متعلقه
    -0.59
    tagext
    -0.59
    {}{}
    -0.58
    moiselle
    -0.57
     referenties
    -0.57
    protoimpl
    -0.57
    POSITIVE LOGITS
     culturelle
    0.55
     végétale
    0.54
     domestiques
    0.52
     cradle
    0.50
     culturelles
    0.50
    dividend
    0.49
    hn
    0.49
     eggs
    0.49
     sauvages
    0.47
     alimentaires
    0.46
    Activations Density 7.427%

    No Known Activations