© 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. 6450
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a positive state or recovery from a negative state

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'well'

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

    positive sentiment

    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
     Audiodateien
    -1.03
    rawDesc
    -0.71
    TagHelper
    -0.68
     NSCoder
    -0.68
    ngdoc
    -0.67
     TestBed
    -0.63
    stateProvider
    -0.62
    nestjs
    -0.62
     تانيه
    -0.60
    SpringBootTest
    -0.58
    POSITIVE LOGITS
     well
    1.91
    well
    1.57
    Well
    1.38
    WELL
    1.37
     Well
    1.34
     WELL
    1.30
     better
    1.19
    better
    1.07
     bien
    0.99
     meglio
    0.96
    Activations Density 0.993%

    No Known Activations