© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10248
    Prev
    Next
    INDEX
    Explanations

    words related to scientific texts and publications

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     newList
    -0.62
     FishBase
    -0.58
    Contours
    -0.54
    printLine
    -0.53
    liputi
    -0.53
    PYX
    -0.52
     defaultstate
    -0.51
     Bakar
    -0.50
    CRR
    -0.50
     BACH
    -0.50
    POSITIVE LOGITS
     חיצוניים
    0.74
     يتيمه
    0.68
    XmlAccessType
    0.66
     שוליים
    0.62
     travailleurs
    0.59
     ProtoMessage
    0.51
     pulseras
    0.49
     ennemis
    0.49
     évit
    0.48
    #+#
    0.47
    Activations Density 1.144%

    No Known Activations