© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14148
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to international business

    oai_token-act-pair · gemini-2.0-flash

    programming and technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    Locations/Countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ://$
    -0.53
    einander
    -0.49
    hæ
    -0.49
     fuo
    -0.47
    endif
    -0.44
    bricht
    -0.44
     superiori
    -0.44
    衛門
    -0.44
     barcel
    -0.43
     bianche
    -0.43
    POSITIVE LOGITS
    fjspx
    1.02
    expandindo
    0.74
     AssemblyCulture
    0.71
    complexContent
    0.70
    CloseOperation
    0.64
    abetes
    0.63
    ########.
    0.61
    yntaxException
    0.60
    TypedDataSet
    0.59
    цездатний
    0.59
    Activations Density 1.283%

    No Known Activations