© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1286
    Prev
    Next
    INDEX
    Explanations

    words and short phrases like "from the", "by the", "property" and "information" that are often used in contracts, documentation, or legal documents.

    oai_token-act-pair · gemini-2.0-flash

    Prepositions of origin/means

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     who
    -0.45
     I
    -0.44
    -
    -0.42
    .
    -0.41
    .,
    -0.41
     she
    -0.41
    teit
    -0.41
    modb
    -0.41
    ъ
    -0.39
    อด
    -0.38
    POSITIVE LOGITS
     незавершена
    0.90
     Monfieur
    0.83
     Anſ
    0.81
     StatefulWidget
    0.80
     myſelf
    0.78
     purpoſe
    0.77
    onAttach
    0.77
     فريبيس
    0.76
     anſ
    0.75
    tanleria
    0.73
    Activations Density 2.171%

    No Known Activations