© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5273
    Prev
    Next
    INDEX
    Explanations

    words related to being accepted or correct

    oai_token-act-pair · gemini-2.0-flash

    welcome

    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
     GenerationType
    -0.70
    NamedQuery
    -0.69
    MockBean
    -0.69
     HasFactory
    -0.69
     CreateTagHelper
    -0.68
     doGet
    -0.67
     WebDriverWait
    -0.67
     JpaRepository
    -0.67
     createState
    -0.66
     interro
    -0.66
    POSITIVE LOGITS
     algum
    0.46
    itola
    0.44
    पया
    0.44
     prav
    0.43
     guste
    0.43
     refusé
    0.43
    hc
    0.43
    hlás
    0.43
     iyon
    0.41
     estudantes
    0.41
    Activations Density 1.796%

    No Known Activations