© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 740
    Prev
    Next
    INDEX
    Explanations

    code snippets or words related to coding and programming such as functions, objects, variables, web addresses and file paths.

    oai_token-act-pair · gemini-2.0-flash

    software configuration

    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
    balleur
    -0.59
     vigor
    -0.56
    Халык
    -0.55
    Welfare
    -0.51
     capital
    -0.50
     drunkenness
    -0.49
     palsy
    -0.49
     thirsty
    -0.49
     vigour
    -0.49
     sobriety
    -0.49
    POSITIVE LOGITS
     stället
    0.50
    featureID
    0.49
     configureStore
    0.48
     pytest
    0.48
     JScrollPane
    0.47
     vscode
    0.46
     zipfile
    0.46
     OpenAPI
    0.45
     MyBatis
    0.44
     ImGui
    0.44
    Activations Density 17.378%

    No Known Activations