© 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. 8236
    Prev
    Next
    INDEX
    Explanations

    Italian references with high activation for dates, locations and the word "edizione"

    oai_token-act-pair · gemini-2.0-flash

    6

    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
     of
    -0.89
    はじめに
    -0.48
     كومونز
    -0.47
     De
    -0.46
    De
    -0.45
    apellido
    -0.45
    তথ্যসূত্র
    -0.44
    tof
    -0.44
    Especificación
    -0.43
     TextInputType
    -0.43
    POSITIVE LOGITS
     di
    0.64
     pinulongan
    0.63
    expandindo
    0.57
    tagHelper
    0.56
    >{@
    0.56
    
    0.54
    期刊论文
    0.54
    TagHelper
    0.54
    IPAC
    0.54
    WireFormatLite
    0.53
    Activations Density 0.293%

    No Known Activations