© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10752
    Prev
    Next
    INDEX
    Explanations

    code-related terms and error messages, especially related to Maven, Java, and Apache

    oai_token-act-pair · gemini-2.0-flash

    Japanese characters 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     critères
    -0.61
     différences
    -0.56
     numéros
    -0.55
     preuves
    -0.55
     sedia
    -0.53
     pouvoirs
    -0.52
     dommages
    -0.52
    ))->
    -0.51
     vérit
    -0.51
     xám
    -0.50
    POSITIVE LOGITS
     pleaſure
    0.55
     Majefty
    0.51
     themſelves
    0.50
     consecration
    0.49
     myſelf
    0.48
     purpoſe
    0.46
     dominions
    0.45
     houſe
    0.44
     himſelf
    0.44
     ſtate
    0.43
    Activations Density 0.315%

    No Known Activations