© 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. 9493
    Prev
    Next
    INDEX
    Explanations

    strings of DNA base pairs, especially those used as primers in PCR

    oai_token-act-pair · gemini-2.0-flash

    primer sequences

    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
     B
    -0.86
    B
    -0.76
    цездатний
    -0.76
    
    -0.65
     BG
    -0.63
     DS
    -0.62
     BH
    -0.61
     LF
    -0.60
    OM
    -0.59
    BM
    -0.59
    POSITIVE LOGITS
    WriteTagHelper
    0.51
    épendant
    0.49
    IsContent
    0.48
    lccn
    0.45
     незавершена
    0.44
    WriteBarrier
    0.43
    vina
    0.43
    TagMode
    0.43
     C
    0.42
    та
    0.42
    Activations Density 4.046%

    No Known Activations