© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially in languages like Java, Javascript and potentially others, with a focus on syntax, keywords, and numerical literals.

    oai_token-act-pair · gemini-2.0-flash

    1

    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
     relâche
    -0.43
    /**
    -0.42
    1
    -0.42
     Picchu
    -0.42
    పు
    -0.40
     ujednoznacz
    -0.38
    ality
    -0.38
    2
    -0.38
     Laughter
    -0.38
    voorbeeld
    -0.35
    POSITIVE LOGITS
     ]
    0.68
    yntaxException
    0.64
    MergeFrom
    0.61
    []);
    0.60
     ());
    0.60
    LabelTagHelper
    0.59
    =?";
    0.59
    gameserver
    0.58
    webElementXpaths
    0.57
    marshaller
    0.57
    Activations Density 16.602%

    No Known Activations