© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2759
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate things are going well or working out

    oai_token-act-pair · gemini-2.0-flash

    Doing/performing well

    np_max-act-logits · gemini-2.0-flash

    say "well/positive adverb"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     good
    -2.16
    good
    -2.05
    Good
    -1.98
     Good
    -1.90
     GOOD
    -1.73
    GOOD
    -1.70
     buena
    -1.42
     bonnes
    -1.40
     buenas
    -1.40
     buen
    -1.39
    POSITIVE LOGITS
    Nearest
    0.51
     المعيارى
    0.50
     mar
    0.48
    +#+
    0.46
    te
    0.44
    inko
    0.42
    beforeAll
    0.42
    sk
    0.42
     _{\
    0.42
    來的
    0.41
    Activations Density 5.295%

    No Known Activations