© 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. 14856
    Prev
    Next
    INDEX
    Explanations

    words pertaining to health, technology, and music, particularly instruments and music.

    oai_token-act-pair · gemini-2.0-flash

    various topics

    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
    <<
    -0.47
     
    -0.46
     <<
    -0.45
    はじめに
    -0.44
    Насе
    -0.42
    }}}}
    -0.38
    ,
    -0.38
    เท้า
    -0.38
     “
    -0.37
    אם
    -0.37
    POSITIVE LOGITS
     Efq
    0.89
     Theſe
    0.87
     Houſe
    0.86
     Monfieur
    0.85
     houſe
    0.85
     myſelf
    0.82
     متعلقه
    0.81
     autorytatywna
    0.79
     المعيارى
    0.79
     ſever
    0.77
    Activations Density 1.010%

    No Known Activations