© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5063
    Prev
    Next
    INDEX
    Explanations

    references to personal thought, feelings, and judgements

    oai_token-act-pair · gemini-2.0-flash

    Opinions and 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     entanto
    -0.48
    著
    -0.47
     such
    -0.45
    engar
    -0.45
    ]._
    -0.45
    виде
    -0.44
    着
    -0.44
    werve
    -0.44
    ませんが
    -0.43
     disse
    -0.42
    POSITIVE LOGITS
    OGND
    0.79
    parsedMessage
    0.78
     referenties
    0.78
     ModelExpression
    0.77
    principalTable
    0.75
    InjectAttribute
    0.74
    InstrumentedTest
    0.74
     Signalez
    0.74
    RegistryLite
    0.72
     للاسماء
    0.72
    Activations Density 1.541%

    No Known Activations