© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12983
    Prev
    Next
    INDEX
    Explanations

    words related to responsibilities and requirements in technical and legal scenarios, as well as words related to studies and school.

    oai_token-act-pair · gemini-2.0-flash

    database entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     itſelf
    -0.89
     myſelf
    -0.87
     faſt
    -0.79
     houſe
    -0.79
    riwal
    -0.78
     Houſe
    -0.77
     ་་
    -0.77
     Monfieur
    -0.77
     himſelf
    -0.76
     Efq
    -0.75
    POSITIVE LOGITS
     alrededores
    0.50
     must
    0.46
    last
    0.44
     for
    0.43
     trust
    0.43
    </b>
    0.43
     last
    0.43
     deve
    0.43
     disputa
    0.42
    臨
    0.41
    Activations Density 0.603%

    No Known Activations