© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8901
    Prev
    Next
    INDEX
    Explanations

    scientific notation for concentrations of chemicals and proteins, particularly those related to immunology, as well as some Japanese characters

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages and code

    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
     Mahomet
    -0.49
    ródło
    -0.48
     NTFS
    -0.48
    jsoup
    -0.46
    ‍♂️
    -0.43
     UEFI
    -0.43
    نسية
    -0.43
     AliExpress
    -0.42
     hentai
    -0.42
    badlogic
    -0.42
    POSITIVE LOGITS
     مرئيه
    0.63
     '\\;'
    0.61
     سكانية
    0.59
     Italijani
    0.57
     Administrativna
    0.57
     estekak
    0.57
    دانشنامهٔ
    0.57
     >=",
    0.56
    Personendaten
    0.55
    UnsafeEnabled
    0.53
    Activations Density 3.539%

    No Known Activations