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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14749
    Prev
    Next
    INDEX
    Explanations

    java code elements like annotations and variable assignments within multithreaded code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Berna
    -0.54
    ссмо
    -0.54
    Refrain
    -0.50
     concealing
    -0.50
     omitting
    -0.49
    habe
    -0.48
     cession
    -0.48
     Broome
    -0.48
    Witam
    -0.48
    enfone
    -0.47
    POSITIVE LOGITS
    MemoryWarning
    0.70
    AnchorTagHelper
    0.62
    migrationBuilder
    0.61
     "..\..\..\
    0.60
     "..\..\
    0.59
    addContainerGap
    0.59
    GroupLayout
    0.58
    modelBuilder
    0.57
    enumi
    0.56
    enumii
    0.55
    Activations Density 2.878%

    No Known Activations