© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    code syntax, including pointers, brackets, and class definitions

    oai_token-act-pair · gemini-2.0-flash

    Code filepaths

    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
     get
    -1.64
     find
    -1.44
     learn
    -1.41
     Get
    -1.39
     create
    -1.38
    get
    -1.27
    Get
    -1.25
     take
    -1.22
     calculate
    -1.20
     determine
    -1.19
    POSITIVE LOGITS
    PCell
    0.49
     humaine
    0.45
     litri
    0.43
     intptr
    0.43
     stratégique
    0.43
     Waray
    0.42
     nød
    0.42
    tvguidetime
    0.41
     étrangère
    0.40
     textStatus
    0.40
    Activations Density 2.311%

    No Known Activations