© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 112
    Prev
    Next
    INDEX
    Explanations

    clauses that include an assessment or judgement.

    oai_token-act-pair · gemini-2.0-flash

    Absence or lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AntiForgeryToken
    -0.84
    styleType
    -0.84
     ModelExpression
    -0.81
    setVerticalGroup
    -0.81
    migrationBuilder
    -0.80
    !*\
    -0.79
     ComVisible
    -0.75
    .*")]
    -0.75
    +#+#
    -0.74
    SharedCtor
    -0.73
    POSITIVE LOGITS
     instead
    0.57
    Instead
    0.54
     Instead
    0.54
    instead
    0.52
     culturale
    0.48
     вместо
    0.46
     istället
    0.45
    default
    0.44
     berupa
    0.44
     bleib
    0.43
    Activations Density 1.772%

    No Known Activations