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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9972
    Prev
    Next
    INDEX
    Explanations

    words associated with dividing a whole into subgroups or components.

    oai_token-act-pair · gemini-2.0-flash

    into

    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
     Efq
    -0.69
     للمعارف
    -0.66
     himſelf
    -0.66
     myſelf
    -0.65
     Diſ
    -0.62
    ChildScrollView
    -0.60
     themſelves
    -0.58
    BeginContext
    -0.58
    PhysRev
    -0.57
     itſelf
    -0.56
    POSITIVE LOGITS
     nî
    0.60
     a
    0.60
    greenrobot
    0.57
    assertRaises
    0.50
    Koordinaten
    0.49
    URLException
    0.49
     potentially
    0.48
     an
    0.47
     trade
    0.46
    versario
    0.46
    Activations Density 0.724%

    No Known Activations