© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9726
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical parts, potentially for a patent.

    oai_token-act-pair · gemini-2.0-flash

    manufacturing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     exceptions
    -0.48
    HasBeenSet
    -0.48
    usammen
    -0.46
     others
    -0.43
     Dey
    -0.43
     nyelven
    -0.42
     поза
    -0.42
     axles
    -0.41
    vetrain
    -0.41
    origins
    -0.41
    POSITIVE LOGITS
    ngdoc
    0.79
     referenties
    0.73
    MENAFN
    0.70
    enterOuterAlt
    0.68
    TabIndex
    0.68
    </tfoot>
    0.67
    __*/
    0.66
     HasFactory
    0.66
    endpush
    0.65
     utafitiHapana
    0.65
    Activations Density 1.996%

    No Known Activations