© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8016
    Prev
    Next
    INDEX
    Explanations

    words describing things that are desired, acquired, or purchased, as well as agreement and people who are doing it.

    oai_token-act-pair · gemini-2.0-flash

    Purchases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -0.70
    SequentialGroup
    -0.60
     CreateTagHelper
    -0.59
    UnitTesting
    -0.57
    Демографія
    -0.56
    InitVars
    -0.55
    ährlich
    -0.54
    astéro
    -0.54
     صوتيه
    -0.52
    Географиясе
    -0.51
    POSITIVE LOGITS
    చు
    0.55
     ferdig
    0.53
    IndentedString
    0.51
     ExecuteAsync
    0.50
     mahdol
    0.49
    gantung
    0.47
    zzá
    0.46
     szüks
    0.46
     Henrietta
    0.46
     fleste
    0.46
    Activations Density 3.153%

    No Known Activations