© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12597
    Prev
    Next
    INDEX
    Explanations

    code, likely related to TFT displays and timers, with numbers and symbols

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pageContext
    -0.40
    دیگر
    -0.39
    ar
    -0.37
     çe
    -0.36
    сс
    -0.36
     banderas
    -0.36
     frères
    -0.36
     ocasião
    -0.35
     Inscrivez
    -0.35
     buona
    -0.35
    POSITIVE LOGITS
    queryInterface
    1.05
     дописавши
    0.88
    SourceChecksum
    0.86
    LookAnd
    0.81
    ]='\
    0.80
    writeFieldEnd
    0.77
     متعلقه
    0.76
    tagHelperRunner
    0.75
     Audiodateien
    0.75
    createCanvas
    0.75
    Activations Density 5.223%

    No Known Activations