© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    the first three letters of the word "Bertram" and names containing them

    oai_token-act-pair · gemini-2.0-flash

    Ber

    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
     contextLoads
    -0.67
     EconPapers
    -0.65
    __(/*!
    -0.65
     تكبرها
    -0.65
     resourceCulture
    -0.64
    WriteBarrier
    -0.63
    ynchronously
    -0.62
     allAfrica
    -0.61
    Referințe
    -0.61
    ,:);
    -0.60
    POSITIVE LOGITS
    garis
    0.51
    吧
    0.48
    decin
    0.46
    naud
    0.45
    rois
    0.45
    nell
    0.44
    nski
    0.44
    kane
    0.44
    endt
    0.43
     laut
    0.42
    Activations Density 9.789%

    No Known Activations