© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    phrases that describe things being turned upside down either literally or figuratively

    oai_token-act-pair · gemini-2.0-flash

    words related to turning or tipping

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

    upside down

    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
    клопе
    -0.59
    })->
    -0.54
    FilterChain
    -0.53
    Izvori
    -0.50
     chew
    -0.49
     ExecuteAsync
    -0.48
    isole
    -0.47
    itonitis
    -0.47
     wä
    -0.46
    ysis
    -0.45
    POSITIVE LOGITS
     tipped
    0.73
     overturned
    0.70
     Turned
    0.68
    Turned
    0.68
     standing
    0.66
     upside
    0.65
     tipping
    0.64
     turned
    0.64
    Standing
    0.64
     Upside
    0.62
    Activations Density 1.375%

    No Known Activations