© 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. 5769
    Prev
    Next
    INDEX
    Explanations

    words that indicate scientific measurement of nutrient intake and deficiencies

    oai_token-act-pair · gemini-2.0-flash

    diet and nutrition

    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
     Administrativna
    -0.60
    itinéraire
    -0.55
    fastjson
    -0.50
     parseFrom
    -0.48
    tagHelperRunner
    -0.48
    setupUi
    -0.47
     Réponses
    -0.46
    Selen
    -0.46
    }$​
    -0.46
    Spiral
    -0.45
    POSITIVE LOGITS
     disjoint
    0.53
     nanop
    0.53
    IsContent
    0.52
     platelets
    0.51
     allergic
    0.50
     histology
    0.50
     dialysis
    0.50
    <bos>
    0.49
     histological
    0.49
    atchewan
    0.48
    Activations Density 14.431%

    No Known Activations