© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15723
    Prev
    Next
    INDEX
    Explanations

    mentions of ideas, rationale, and design.

    oai_token-act-pair · gemini-2.0-flash

    idea

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    webElementXpaths
    -0.98
    ConstraintMaker
    -0.89
     FetchType
    -0.84
    "])
    -0.83
     =>
    -0.82
    ]--;
    -0.80
    extAlignment
    -0.79
    存于互联网档案馆
    -0.79
    PhysRevLett
    -0.78
    protoimpl
    -0.77
    POSITIVE LOGITS
     behind
    0.59
    nel
    0.49
     for
    0.47
     of
    0.47
    нок
    0.45
     پشت
    0.42
    behind
    0.42
    fort
    0.41
     atrás
    0.40
    Tags
    0.40
    Activations Density 3.055%

    No Known Activations