© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4416
    Prev
    Next
    INDEX
    Explanations

    content related to academic writing and research.

    oai_token-act-pair · gemini-2.0-flash

    technical/academic writing

    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
    ільки
    -0.55
     NUKAT
    -0.53
    скі
    -0.48
     and
    -0.48
    чені
    -0.47
    сі
    -0.46
     Архів
    -0.46
    extAlignment
    -0.46
    toz
    -0.45
    іль
    -0.45
    POSITIVE LOGITS
     bezeichneter
    0.76
    orteur
    0.62
    MessageTagHelper
    0.59
    parsedMessage
    0.59
     mergeFrom
    0.58
    AnchorTagHelper
    0.55
    RunAsync
    0.54
     kreatif
    0.53
    Wikis
    0.53
     Bessel
    0.53
    Activations Density 2.141%

    No Known Activations