© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2238
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation marks, possibly delimiting a cooking or recipe context

    oai_token-act-pair · 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
    ENCIAS
    -0.57
     shave
    -0.54
     Histórico
    -0.53
     tiro
    -0.52
     unwind
    -0.52
     burn
    -0.50
    phòng
    -0.49
     thicken
    -0.49
     shape
    -0.49
     quench
    -0.48
    POSITIVE LOGITS
    httphttps
    0.65
     ujednoznacz
    0.62
     wikipagina
    0.61
     resourceCulture
    0.52
    Pur
    0.52
    Will
    0.51
    mergeFrom
    0.50
    Don
    0.50
    Bree
    0.48
     Tries
    0.47
    Activations Density 6.353%

    No Known Activations