© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    code that contains the words 'foo', 'bar' and numbers

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    <bos>
    -0.73
    таратура
    -0.48
     thất
    -0.42
    labus
    -0.40
    เท
    -0.40
    tières
    -0.40
    ATURA
    -0.38
     :
    -0.37
    سل
    -0.37
     των
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.52
     يتيمه
    0.49
    AlterField
    0.49
    ValueGeneration
    0.48
     OFDb
    0.48
     Juarez
    0.47
    SPATH
    0.47
    sidemargin
    0.47
    Pautan
    0.47
     consultato
    0.46
    Activations Density 1.347%

    No Known Activations