© 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. 14067
    Prev
    Next
    INDEX
    Explanations

    computer code or mathematical expressions, including variables, functions, and operators from programming languages

    oai_token-act-pair · gemini-2.0-flash

    Geometric drawing code

    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
    ModelAdmin
    -0.65
     الرخصة
    -0.61
     سكانية
    -0.61
    PreAuthorize
    -0.60
    URLException
    -0.60
    SPATH
    -0.59
     unknownFields
    -0.58
    ParallelGroup
    -0.58
     propOrder
    -0.58
     ويكيميديا
    -0.55
    POSITIVE LOGITS
     ball
    0.50
     wheel
    0.49
     Point
    0.47
     turning
    0.45
     Turning
    0.45
    yesha
    0.43
     sphere
    0.43
     يتيمه
    0.43
    turning
    0.43
     Turn
    0.42
    Activations Density 4.209%

    No Known Activations