© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms mostly related to pharmaceuticals and chemical compounds.

    oai_token-act-pair · gemini-2.0-flash

    medications

    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
     ivelany
    -0.58
     EconPapers
    -0.55
     esternos
    -0.54
     cherchés
    -0.54
    rrggbb
    -0.51
     فريبيس
    -0.44
     rumahnya
    -0.42
    "},
    -0.41
    ubwa
    -0.40
     talleres
    -0.40
    POSITIVE LOGITS
    omycin
    0.85
    razine
    0.84
    azine
    0.78
    conazole
    0.73
    ulfate
    0.72
    floxacin
    0.70
    profen
    0.69
    ocin
    0.68
    oxone
    0.68
     toxin
    0.68
    Activations Density 11.197%

    No Known Activations