© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    code snippets in php and java that contain comments and annotations

    oai_token-act-pair · gemini-2.0-flash

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Jefus
    -0.73
     $_"
    -0.72
     myſelf
    -0.72
     iſt
    -0.71
     ainfi
    -0.69
     auffi
    -0.68
    neſs
    -0.68
     Efq
    -0.68
    ^(@)
    -0.67
     Eſ
    -0.67
    POSITIVE LOGITS
     
    0.81
     M
    0.59
     for
    0.59
     W
    0.59
     le
    0.59
     s
    0.57
     N
    0.55
    complexContent
    0.53
     se
    0.53
     T
    0.53
    Activations Density 5.309%

    No Known Activations