© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    verbs related to understanding and planning in the context of personal experiences

    oai_token-act-pair · gemini-2.0-flash

    figure

    np_max-act · 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
    Negative Logits
     LoginComponent
    -0.61
    addImage
    -0.58
    haustible
    -0.56
    OkHttpClient
    -0.56
    ScreenState
    -0.55
     Llor
    -0.55
    ]--;
    -0.54
    peth
    -0.54
     neighbour
    -0.53
     Favourite
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.84
    первых
    0.75
     idéia
    0.75
     tying
    0.65
    RegistryLite
    0.59
    contentLoaded
    0.58
     listos
    0.58
    StoreMessageInfo
    0.58
     particularmente
    0.57
     poveznice
    0.57
    Activations Density 1.817%

    No Known Activations