© 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. 6545
    Prev
    Next
    INDEX
    Explanations

    the word "good."

    oai_token-act-pair · gemini-2.0-flash

    the word "good"

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

    good

    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
     marbre
    -0.53
     nessuno
    -0.49
     déclar
    -0.48
     aveug
    -0.45
     missão
    -0.44
    :].
    -0.44
     Commitment
    -0.43
     générations
    -0.43
     modèle
    -0.42
     området
    -0.42
    POSITIVE LOGITS
    
    0.78
     EconPapers
    0.73
     مشين
    0.72
    EndGlobalSection
    0.72
    principalTable
    0.69
    IndentedString
    0.69
    classnames
    0.68
    ContentAsync
    0.66
    FailureListener
    0.66
     newBuilder
    0.65
    Activations Density 0.502%

    No Known Activations