© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    positive descriptors, sometimes related to being maintained or in good condition

    oai_token-act-pair · gemini-2.0-flash

    Quality/condition of something

    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
     sát
    -0.56
    fjspx
    -0.50
    Personensuche
    -0.47
    avon
    -0.46
     disambiguazione
    -0.45
    ondis
    -0.44
     Arden
    -0.43
    عداد
    -0.42
     صوتيه
    -0.42
     Intention
    -0.42
    POSITIVE LOGITS
     XCTest
    0.74
    styleUrls
    0.66
    parsedMessage
    0.64
     kasarigan
    0.63
    CppMethod
    0.61
    findpost
    0.61
    rzej
    0.60
     referenties
    0.60
    elemField
    0.59
    eaways
    0.59
    Activations Density 3.786%

    No Known Activations