© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5058
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical likelihood and comparisons.

    oai_token-act-pair · gemini-2.0-flash

    study results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     highly
    -0.71
    Highly
    -0.68
    highly
    -0.66
     Highly
    -0.64
    kháu
    -0.60
    ArgsConstructor
    -0.57
    Искәрмәләр
    -0.57
     arşivlendi
    -0.56
     numberOfRows
    -0.56
    HtmlAttribute
    -0.54
    POSITIVE LOGITS
    ázaro
    0.59
     découver
    0.57
    _{-\
    0.52
    protoimpl
    0.52
    homonymie
    0.51
    zyms
    0.51
    nyata
    0.51
    reuung
    0.50
     Conclusions
    0.50
     Understand
    0.49
    Activations Density 1.007%

    No Known Activations