© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13469
    Prev
    Next
    INDEX
    Explanations

    descriptions of commercial services or products and related business activities

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    RegressionTest
    -0.85
    tamol
    -0.61
    /**
    -0.60
     <=",
    -0.59
    
    -0.58
    enderror
    -0.56
    ValueGeneration
    -0.56
    uchter
    -0.53
    ^(@
    -0.51
     समीक्षाएं
    -0.51
    POSITIVE LOGITS
    XmlAccessorType
    0.61
    XmlAccessType
    0.55
     مشين
    0.54
    Према
    0.53
     eternal
    0.48
    fiable
    0.47
    нале
    0.47
     consumer
    0.46
    aspectj
    0.46
    RunWith
    0.45
    Activations Density 1.011%

    No Known Activations