© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6817
    Prev
    Next
    INDEX
    Explanations

    sentences where a person is thinking about what they or another person believes, knows, or feels

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    queryInterface
    -0.76
    NameInMap
    -0.61
    igshid
    -0.60
    onViewCreated
    -0.52
    دانشنامهٔ
    -0.52
    FunctionFlags
    -0.51
     tertarik
    -0.51
    RegistryLite
    -0.50
    ApiModel
    -0.50
    الصفحه
    -0.49
    POSITIVE LOGITS
    should
    0.61
     ought
    0.59
     should
    0.58
    Should
    0.58
    SequentialGroup
    0.56
     deveria
    0.54
     Should
    0.54
     EnglishChoose
    0.53
     dever
    0.53
     fhould
    0.52
    Activations Density 1.978%

    No Known Activations