© 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. 12436
    Prev
    Next
    INDEX
    Explanations

    seemingly random code snippets with a slight preference for tags and functions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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>
    -0.84
    enumii
    -0.69
    rungsseite
    -0.69
     незавершена
    -0.68
    webElementGuid
    -0.67
    extAlignment
    -0.62
    rizona
    -0.61
     للمعارف
    -0.58
    __*/
    -0.58
    Scénario
    -0.56
    POSITIVE LOGITS
    …~
    0.50
    residence
    0.50
     useSelector
    0.49
     fermés
    0.48
     跳转至
    0.48
     Hail
    0.47
     useDispatch
    0.47
     traités
    0.46
    HttpEntity
    0.44
     originales
    0.44
    Activations Density 0.898%

    No Known Activations