© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9570
    Prev
    Next
    INDEX
    Explanations

    the boolean values "true" and "false", sometimes in conjunction with "equal"

    oai_token-act-pair · gemini-2.0-flash

    boolean equivalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    StoryboardSegue
    -1.03
     CreateTagHelper
    -0.92
    SharedDtor
    -0.89
    Espèce
    -0.86
     BrowserModule
    -0.84
    SizeMode
    -0.84
     AssemblyProduct
    -0.81
     "..\..\
    -0.81
    Hochspringen
    -0.81
    tonsoft
    -0.77
    POSITIVE LOGITS
    <bos>
    1.69
     tačiau
    0.57
    '
    0.57
    By
    0.57
    is
    0.55
    I
    0.48
    The
    0.48
    We
    0.48
    on
    0.47
    -
    0.47
    Activations Density 0.504%

    No Known Activations