© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15158
    Prev
    Next
    INDEX
    Explanations

    places where comparison operations are performed, often using words and phrases like "compared to", "counterparts", and "versus"

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AndEndTag
    -0.71
    Дереккөздер
    -0.69
    SizeMode
    -0.64
    RepeatedField
    -0.60
    Rhestr
    -0.60
    SharedCtor
    -0.60
    AccessorTable
    -0.59
    IndentedString
    -0.58
    Abit
    -0.57
     InputDecoration
    -0.57
    POSITIVE LOGITS
    rodalom
    0.46
    ANDUM
    0.44
    SuspendLayout
    0.43
    hånd
    0.42
     kautta
    0.41
     pé
    0.40
     избе
    0.40
     Drittel
    0.39
     itulah
    0.38
    postIndex
    0.38
    Activations Density 23.272%

    No Known Activations