© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    code snippets like variable names, function definitions, and include statements

    oai_token-act-pair · gemini-2.0-flash

    computer 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
     Bul
    -1.69
     Bur
    -1.68
     Bu
    -1.63
    Bul
    -1.62
     Buff
    -1.62
     BUR
    -1.59
    Bur
    -1.58
     Bull
    -1.58
    Bull
    -1.57
     bul
    -1.55
    POSITIVE LOGITS
     consultato
    0.49
    lä
    0.47
    fä
    0.45
    minecraftforge
    0.44
    égio
    0.43
     Gleason
    0.43
     Fisch
    0.41
     Casas
    0.41
    cshtml
    0.41
    raim
    0.41
    Activations Density 1.139%

    No Known Activations