© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12278
    Prev
    Next
    INDEX
    Explanations

    conditional phrases offering alternative solutions

    oai_token-act-pair · gemini-2.0-flash

    possibility/actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     مرئيه
    -0.78
     الرياضيه
    -0.78
    новниш
    -0.74
    TintMode
    -0.73
     himo
    -0.73
     unknownFields
    -0.73
     Picchu
    -0.71
     transfieras
    -0.71
    تقاوى
    -0.66
    хьтан
    -0.65
    POSITIVE LOGITS
     onCreateView
    0.51
    這位
    0.46
    hofen
    0.43
    ReadInt
    0.43
    hofer
    0.43
    ValueStyle
    0.42
    这位
    0.42
    pard
    0.41
    glPopMatrix
    0.41
    gı
    0.41
    Activations Density 1.302%

    No Known Activations