© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2366
    Prev
    Next
    INDEX
    Explanations

    sentence fragments that have a verb connecting two nouns or pronouns

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    sidemargin
    -0.57
     Muc
    -0.56
     juges
    -0.54
    $~
    -0.51
    Хьажоргаш
    -0.51
    UserDao
    -0.51
     FontFamily
    -0.51
    OrBuilder
    -0.50
     canais
    -0.49
    󠁥
    -0.49
    POSITIVE LOGITS
    <bos>
    0.59
    Życiorys
    0.56
     hennes
    0.49
     cố
    0.48
     disponibilités
    0.47
     hiszen
    0.46
    archiviato
    0.46
     LoggerFactory
    0.46
    horabuena
    0.46
    meist
    0.45
    Activations Density 1.571%

    No Known Activations