© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8097
    Prev
    Next
    INDEX
    Explanations

    words with a high "ky" sound followed by "ba" or "an" and names starting with A or containing "thy."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     الحره
    -0.77
     NSCoder
    -0.75
    ]),
    -0.75
    NUMX
    -0.74
    </>
    -0.73
     disambiguazione
    -0.73
    CardContent
    -0.71
    Viitteet
    -0.69
    endpush
    -0.68
     jScrollPane
    -0.67
    POSITIVE LOGITS
     cortesía
    0.56
    ICY
    0.55
     swat
    0.51
     visst
    0.51
     across
    0.50
     varying
    0.50
     malos
    0.49
     skle
    0.49
     nebst
    0.49
     secco
    0.48
    Activations Density 1.185%

    No Known Activations