© 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. 6895
    Prev
    Next
    INDEX
    Explanations

    Vietnamese place names

    oai_token-act-pair · gemini-2.0-flash

    Vietnamese text

    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
     tiens
    -0.63
    SharedDtor
    -0.59
     voudrais
    -0.57
     pinulongan
    -0.54
     vulgaires
    -0.54
    SourceChecksum
    -0.53
    ьогодні
    -0.53
    мерть
    -0.52
     huellas
    -0.52
     meurt
    -0.52
    POSITIVE LOGITS
    ậm
    0.98
    ẫ
    0.96
    ấc
    0.96
    ẫy
    0.95
    ưỡi
    0.94
    ợn
    0.93
    ứa
    0.93
    ườ
    0.91
    ượ
    0.91
    ượt
    0.91
    Activations Density 0.687%

    No Known Activations