© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13640
    Prev
    Next
    INDEX
    Explanations

    code snippets in JSON objects with properties 'language' and 'title'

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personensuche
    -0.71
     hObject
    -0.67
    tonode
    -0.66
    IndentedString
    -0.64
     EconPapers
    -0.59
     SPOILERS
    -0.58
     uniqlo
    -0.57
    InjectAttribute
    -0.57
     Francine
    -0.57
     CURLOPT
    -0.56
    POSITIVE LOGITS
    "}")
    0.67
    <>());
    0.60
    })$}
    0.60
    "");
    0.59
    '],$
    0.56
    [])
    0.56
    ()],
    0.55
    ++]=
    0.55
    "}";
    0.54
    ']:
    0.52
    Activations Density 1.859%

    No Known Activations