© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4135
    Prev
    Next
    INDEX
    Explanations

    words preceding definite articles and prepositions, as well as numbers and court-related terms.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    EndContext
    -1.06
    NameInMap
    -1.02
     HasFactory
    -0.84
    存于互联网档案馆
    -0.84
    CloseOperation
    -0.83
     يتيمه
    -0.81
    Personensuche
    -0.78
     Efq
    -0.77
    AnimationsModule
    -0.77
    UnknownFields
    -0.76
    POSITIVE LOGITS
     ger
    0.57
     ta
    0.52
    reto
    0.51
     lang
    0.49
    psum
    0.49
    振
    0.47
    evo
    0.47
    uero
    0.47
    nale
    0.46
     Haller
    0.46
    Activations Density 6.269%

    No Known Activations