© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    various function words such as pronouns, prepositions, and determiners in different languages, as well as words indicating quantification

    oai_token-act-pair · gemini-2.0-flash

    each

    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
    saga
    -0.52
    HomeAsUpEnabled
    -0.50
    cshtml
    -0.49
     am
    -0.48
    cet
    -0.47
     av
    -0.47
     the
    -0.46
    sans
    -0.45
     #
    -0.44
    canny
    -0.44
    POSITIVE LOGITS
    żdy
    1.02
     ciasc
    0.91
    each
    0.90
     each
    0.89
     ciascuno
    0.85
    EACH
    0.85
    Each
    0.85
     bawat
    0.84
     chacune
    0.84
     Ogni
    0.84
    Activations Density 0.475%

    No Known Activations