© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11473
    Prev
    Next
    INDEX
    Explanations

    markup or code from programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets with special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     chrétien
    -0.58
     közül
    -0.58
     supérieurs
    -0.56
     confirmer
    -0.53
     juges
    -0.52
     követ
    -0.49
     circonstances
    -0.49
     brazo
    -0.48
     anledning
    -0.48
     pauvres
    -0.47
    POSITIVE LOGITS
     ExecuteAsync
    1.13
     ་་
    1.09
    ſelf
    1.09
    SharedDtor
    1.08
    Cyfeiriadau
    1.08
     crdi
    1.08
    CppCodeGen
    1.07
     Forumite
    1.05
     GenerationType
    1.04
    ".
    1.03
    Activations Density 97.153%

    No Known Activations