© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    what appear to be C language code snippets relating to memory synchronization and file access, and legal/testimony language

    oai_token-act-pair · gemini-2.0-flash

    YNC

    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
     surla
    -0.64
     виправивши
    -0.60
    antMatchers
    -0.59
    s
    -0.58
    idens
    -0.53
     beginnetje
    -0.52
     Lors
    -0.52
    IUrlHelper
    -0.50
    🏾
    -0.49
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    ✷
    0.78
    ❹
    0.77
     realised
    0.75
     čierna
    0.75
     specialises
    0.74
     labouring
    0.73
    SPATH
    0.72
     realising
    0.71
     unauthorised
    0.70
    arised
    0.70
    Activations Density 9.811%

    No Known Activations