© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10001
    Prev
    Next
    INDEX
    Explanations

    code-like text or descriptions of structured experiments.

    oai_token-act-pair · gemini-2.0-flash

    Technical document fragments

    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
     initComponents
    -0.76
     surla
    -0.69
    EndInit
    -0.60
    XMLSchema
    -0.60
     FetchType
    -0.59
    RSpec
    -0.56
     Cey
    -0.53
    weixin
    -0.53
    complexContent
    -0.52
    ViewById
    -0.51
    POSITIVE LOGITS
     rağmen
    0.59
    ofire
    0.50
     träd
    0.46
     dön
    0.46
    stateParams
    0.46
    ToTensor
    0.45
     déroule
    0.44
     dönd
    0.44
     الاطلاع
    0.44
     måneder
    0.44
    Activations Density 0.232%

    No Known Activations