© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10863
    Prev
    Next
    INDEX
    Explanations

    words and characters from languages other than English

    oai_token-act-pair · gemini-2.0-flash

    Blog posts and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Administrativna
    -0.57
    RectangleBorder
    -0.52
    abstractmethod
    -0.49
     createState
    -0.49
     peine
    -0.48
     renseignements
    -0.47
     typelib
    -0.47
     pun
    -0.45
     giudi
    -0.45
     torno
    -0.44
    POSITIVE LOGITS
     feveral
    0.64
     Chriftian
    0.60
     Majefty
    0.59
    :✨
    0.59
    forChild
    0.57
     ſeveral
    0.56
    StructEnd
    0.56
     neceff
    0.55
     poffe
    0.54
     fevere
    0.54
    Activations Density 0.338%

    No Known Activations