© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9826
    Prev
    Next
    INDEX
    Explanations

    words related to medical studies, research, and suggestions that are being made

    oai_token-act-pair · gemini-2.0-flash

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    further
    -1.21
     further
    -1.21
    Further
    -1.20
     Further
    -1.17
     FURTHER
    -1.09
    FURTHER
    -0.93
    urther
    -0.83
     farther
    -0.74
     дальней
    -0.68
    进一步
    -0.67
    POSITIVE LOGITS
    bootstrapcdn
    0.77
     виправивши
    0.73
    TagMode
    0.71
     للمعارف
    0.66
    Diweddarwch
    0.66
    исленность
    0.65
    Kanpo
    0.60
    TestingModule
    0.59
    ThroughAttribute
    0.59
    aarrggbb
    0.58
    Activations Density 16.154%

    No Known Activations