Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2308
    Prev
    Next
    INDEX
    Explanations

    scientific research paper snippets involving chemical and biological toxicity, measurements, or testing.

    oai_token-act-pair · gemini-2.0-flash

    toxicity in scientific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.68
     oprot
    -0.63
    IndentedString
    -0.62
    sizeCache
    -0.60
     AspNetCore
    -0.60
    StoryboardSegue
    -0.59
    发表于
    -0.59
    istoitu
    -0.58
    NameInMap
    -0.58
     مشين
    -0.58
    POSITIVE LOGITS
     pherom
    0.56
    ethylene
    0.52
    meetings
    0.51
    farwyddwr
    0.50
    red
    0.50
     Antigen
    0.50
     OnTriggerEnter
    0.49
     surfactants
    0.49
     prostagland
    0.49
     Variation
    0.49
    Activations Density 11.982%

    No Known Activations