© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    code and pathnames.

    oai_token-act-pair · gemini-2.0-flash

    code snippets URLs

    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
    .
    -1.43
    NameInMap
    -0.82
    TestingModule
    -0.73
    ReusableCell
    -0.66
    Demografie
    -0.62
     protoimpl
    -0.62
    findpost
    -0.61
    TagMode
    -0.55
     GenerationType
    -0.52
    VIAF
    -0.52
    POSITIVE LOGITS
     Com
    0.54
    Facades
    0.53
    TypedDataSet
    0.51
     particulières
    0.48
    uksi
    0.48
    omorphology
    0.48
    точка
    0.47
     com
    0.47
    (!_
    0.47
    arate
    0.47
    Activations Density 2.247%

    No Known Activations