© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    words and phrases in Spanish and Portuguese, also code snippets

    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
     recommended
    -0.49
    ьажоргаш
    -0.47
     the
    -0.47
     logically
    -0.46
    ModelAdmin
    -0.44
     <",
    -0.43
    < 
    -0.41
    หว่าง
    -0.41
     read
    -0.41
     missed
    -0.41
    POSITIVE LOGITS
    原始内容存档于
    0.60
    inginan
    0.57
    mampuan
    0.56
    vención
    0.53
     desmotivaciones
    0.52
     boî
    0.51
    guenos
    0.50
     AssemblyCulture
    0.50
    ANEOUS
    0.50
    TestingModule
    0.49
    Activations Density 3.669%

    No Known Activations