© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9884
    Prev
    Next
    INDEX
    Explanations

    words which start a phrase or clause, especially prepositions

    oai_token-act-pair · gemini-2.0-flash

    Long, repetitive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    InjectAttribute
    -0.97
     EconPapers
    -0.89
    __':
    -0.84
    SharedDtor
    -0.81
     ModelExpression
    -0.81
    tagHelperRunner
    -0.81
    InstrumentedTest
    -0.79
    Personendaten
    -0.76
    RectangleBorder
    -0.76
     defaultstate
    -0.75
    POSITIVE LOGITS
    sty
    0.49
     kru
    0.47
     "$
    0.46
     Blan
    0.46
    tico
    0.45
    առ
    0.44
     Kru
    0.44
    ικ
    0.44
     support
    0.44
    ach
    0.43
    Activations Density 35.726%

    No Known Activations