© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical research and cancer treatment

    oai_token-act-pair · gemini-2.0-flash

    Medical and surgical contexts

    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
     simplifié
    -0.46
    }_\
    -0.46
     Minim
    -0.45
     SEDS
    -0.44
     heen
    -0.43
     sedia
    -0.43
     Pelican
    -0.43
    pela
    -0.42
    合併
    -0.42
     TimeUnit
    -0.42
    POSITIVE LOGITS
     GenerationType
    0.75
     disambiguazione
    0.67
     nakalista
    0.66
     defStyleAttr
    0.65
    ništ
    0.65
    rungsseite
    0.62
    Chham
    0.59
    CppMethod
    0.58
    expandindo
    0.57
     nahilalakip
    0.55
    Activations Density 8.248%

    No Known Activations