© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1419
    Prev
    Next
    INDEX
    Explanations

    syntax and special characters used in computer programming, such as quotation marks, brackets, and colons

    oai_token-act-pair · gemini-2.0-flash

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ANTLR
    -0.54
    ́i
    -0.49
     Red
    -0.48
     biên
    -0.48
     I
    -0.47
     present
    -0.44
     "
    -0.44
    ReferenceEquals
    -0.43
     her
    -0.43
     S
    -0.42
    POSITIVE LOGITS
     purpoſe
    0.70
     raiſ
    0.69
    ագրություններ
    0.68
     fubject
    0.65
     fuper
    0.65
     neceffary
    0.65
    tidaknya
    0.65
     becauſe
    0.65
    ьаж
    0.63
     themſelves
    0.63
    Activations Density 1.470%

    No Known Activations