© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15900
    Prev
    Next
    INDEX
    Explanations

    the word "edition", and sometimes the letter "S" directly preceding it

    oai_token-act-pair · gemini-2.0-flash

    edition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    رشف
    -0.94
    Хьажоргаш
    -0.88
     Offisielt
    -0.83
     gyhoeddwyd
    -0.81
     sabbia
    -0.81
    󠁴
    -0.80
     photolibrary
    -0.79
    MenuGroup
    -0.79
     <>",
    -0.77
     clearColor
    -0.77
    POSITIVE LOGITS
    ci
    0.60
     kaynağından
    0.53
    ly
    0.53
     consequ
    0.52
     <
    0.52
    t
    0.51
    mer
    0.50
    s
    0.50
    operatorname
    0.50
    me
    0.49
    Activations Density 0.547%

    No Known Activations