© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10687
    Prev
    Next
    INDEX
    Explanations

    what looks like source code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
    iten
    -0.41
    lah
    -0.40
    ↵↵
    -0.40
     ((
    -0.39
     plus
    -0.39
     им
    -0.39
    plus
    -0.38
    iformis
    -0.38
    </i>
    -0.38
    */
    -0.38
    POSITIVE LOGITS
    ⓧ
    0.85
     Majefty
    0.81
     Chriftian
    0.80
     ModelExpression
    0.79
     Efq
    0.77
    ^(@)
    0.76
     themſelves
    0.74
     myſelf
    0.74
     becauſe
    0.72
     विश्वसनीयता
    0.72
    Activations Density 2.173%

    No Known Activations