© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to computer code and scientific writing

    oai_token-act-pair · gemini-2.0-flash

    technical publications

    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
    BeginContext
    -0.34
    ✭✭
    -0.31
     تضيفلها
    -0.29
    rungsseite
    -0.29
    Rhestr
    -0.29
     Exactos
    -0.29
    UserScript
    -0.29
     Chwiliwch
    -0.28
     springfox
    -0.28
    Życiorys
    -0.28
    POSITIVE LOGITS
    tin
    0.90
    ting
    0.85
    tn
    0.84
    tk
    0.82
    ti
    0.82
    ten
    0.82
    td
    0.82
    ty
    0.81
    tes
    0.81
    tus
    0.80
    Activations Density 6.181%

    No Known Activations