© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    context clues such as "at", "the", "a", etc

    oai_token-act-pair · gemini-2.0-flash

    at home

    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
     Home
    -2.66
    Home
    -2.63
     HOME
    -2.53
     home
    -2.47
    home
    -2.41
    HOME
    -2.39
     homes
    -2.39
     Homes
    -2.34
    homes
    -2.17
     house
    -2.14
    POSITIVE LOGITS
     surla
    0.59
    хьтан
    0.51
    RTLD
    0.48
     beginnetje
    0.47
     صوتيه
    0.45
     &___
    0.45
    lrrrr
    0.44
     Murch
    0.44
    Rptr
    0.44
     мәкал
    0.44
    Activations Density 1.271%

    No Known Activations