© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1247
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated word fragments and proper nouns

    oai_token-act-pair · gemini-2.0-flash

    say "Br" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Personendaten
    -0.82
     الحره
    -0.79
     kasarigan
    -0.77
     للمعارف
    -0.77
    Portail
    -0.75
    protoimpl
    -0.75
     صوتيه
    -0.72
    InjectAttribute
    -0.72
     autorytatywna
    -0.69
     <=",
    -0.68
    POSITIVE LOGITS
     Dre
    0.72
    bro
    0.71
    bra
    0.69
    bru
    0.69
     DRE
    0.68
     Bra
    0.67
     Kra
    0.67
    dre
    0.66
    cro
    0.66
     Tre
    0.66
    Activations Density 5.767%

    No Known Activations