© 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. 3963
    Prev
    Next
    INDEX
    Explanations

    mentions of spans of time (days, weeks)

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    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
    enderror
    -1.12
    UnusedPrivate
    -0.91
     Mahomet
    -0.85
    oredCriteria
    -0.85
     propOrder
    -0.83
     Britann
    -0.82
    mergeFrom
    -0.82
     Realt
    -0.81
     initComponents
    -0.81
    NUMX
    -0.80
    POSITIVE LOGITS
    :
    0.49
     portátiles
    0.43
     sogget
    0.41
     stratégies
    0.41
     hombros
    0.40
     avrà
    0.38
     arbres
    0.38
     volna
    0.38
     attiv
    0.37
     têtes
    0.37
    Activations Density 0.047%

    No Known Activations