© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14714
    Prev
    Next
    INDEX
    Explanations

    prepositions, conjunctions, and function words that specify relationships between people or concepts.

    oai_token-act-pair · gemini-2.0-flash

    Under control/management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    MethodManager
    -0.60
    ]]]
    -0.56
     consultato
    -0.53
     rato
    -0.51
    nessed
    -0.51
     androidx
    -0.51
     trade
    -0.51
    PhysRev
    -0.50
     apart
    -0.50
    voer
    -0.50
    POSITIVE LOGITS
    principalColumn
    0.71
    istible
    0.68
    parsedMessage
    0.67
    <?
    0.64
    /**
    0.63
    
    0.60
    RTEX
    0.60
    nvarchar
    0.58
     okuyayım
    0.58
     MainAxisSize
    0.57
    Activations Density 4.231%

    No Known Activations