© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9165
    Prev
    Next
    INDEX
    Explanations

    code snippets and numerical comparisons

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.61
    ORC
    -0.50
    OrEqualTo
    -0.50
     lagt
    -0.47
     refills
    -0.46
     dessous
    -0.45
     mukana
    -0.44
    enumii
    -0.44
     newOwner
    -0.43
     aload
    -0.42
    POSITIVE LOGITS
     NSCoder
    0.72
     ProtoMessage
    0.69
     propOrder
    0.65
     समीक्षक
    0.60
    TestingModule
    0.57
    __(/*!
    0.57
     unknownFields
    0.56
    TestBed
    0.55
    hawat
    0.54
    SafeMath
    0.54
    Activations Density 1.507%

    No Known Activations