© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11965
    Prev
    Next
    INDEX
    Explanations

    words starting with "dis" or "in" followed by other letters, especially when they indicate opposition or negation

    oai_token-act-pair · gemini-2.0-flash

    adjectives indicating quality or reliability

    np_token-act-pair-logits · gpt-4o-mini

    in or dis prefixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CloseOperation
    -0.65
    انجليز
    -0.61
    losigkeit
    -0.59
    RunAsync
    -0.53
    zupeł
    -0.52
     misled
    -0.51
     fausse
    -0.50
    deviation
    -0.50
    ecture
    -0.50
     unclear
    -0.50
    POSITIVE LOGITS
     adequate
    0.72
     reliable
    0.69
     properly
    0.68
     competent
    0.68
     coherent
    0.67
     appropriate
    0.63
     trustworthy
    0.63
     proper
    0.62
     satisfactory
    0.60
     Properly
    0.60
    Activations Density 3.294%

    No Known Activations