© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7713
    Prev
    Next
    INDEX
    Explanations

    words from languages other than English

    oai_token-act-pair · gemini-2.0-flash

    French negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     päät
    -0.55
     du
    -0.53
    govor
    -0.52
     näytte
    -0.52
     gave
    -0.52
    mazoo
    -0.52
     por
    -0.51
     took
    -0.50
    ทรง
    -0.49
    }}+\
    -0.49
    POSITIVE LOGITS
    Rüyada
    0.93
    SpringBootTest
    0.90
     للمعارف
    0.82
    VolleyError
    0.81
    脚注の使い方
    0.77
    +:+
    0.76
    PreferredItem
    0.76
     ivelany
    0.75
     initComponents
    0.73
    CppMethod
    0.73
    Activations Density 0.210%

    No Known Activations