© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11889
    Prev
    Next
    INDEX
    Explanations

    fragments of non-English text related to user interfaces

    oai_token-act-pair · gemini-2.0-flash

    drž

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UTIONS
    -0.54
     oral
    -0.53
     C
    -0.52
     onData
    -0.51
     y
    -0.51
    hanna
    -0.51
     Hartley
    -0.50
     li
    -0.49
    observer
    -0.49
    oral
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.86
    styleType
    0.81
     Reverso
    0.81
     nahilalakip
    0.80
    rungsseite
    0.75
    NameInMap
    0.74
    Personendaten
    0.70
    
    0.70
     OFDb
    0.69
     nakalista
    0.69
    Activations Density 0.986%

    No Known Activations