© 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. 6390
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially constants (e.g. variable/macro names) often all in uppercase, with underscores

    oai_token-act-pair · gemini-2.0-flash

    underscore

    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
    in
    -1.17
    h
    -1.02
    on
    -1.02
    to
    -1.00
    is
    -0.98
    an
    -0.97
    m
    -0.96
    k
    -0.96
    f
    -0.95
    w
    -0.95
    POSITIVE LOGITS
     المعيارى
    0.75
    adeloupe
    0.73
    iffance
    0.70
     CreateTagHelper
    0.70
    ifolium
    0.66
    æus
    0.63
    ervations
    0.63
    setLayoutManager
    0.63
    redient
    0.62
    SequentialGroup
    0.61
    Activations Density 1.706%

    No Known Activations