© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6897
    Prev
    Next
    INDEX
    Explanations

    the word "mind" with other words related to thinking, ideas, copyright or community

    oai_token-act-pair · gemini-2.0-flash

    mind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ValueStyle
    -0.74
    ArrowToggle
    -0.73
     يتيمه
    -0.71
    SourceChecksum
    -0.69
    日閲覧
    -0.67
    principalTable
    -0.65
    olisian
    -0.64
    ContentAsync
    -0.61
    \"></
    -0.61
    RegistryLite
    -0.60
    POSITIVE LOGITS
    gas
    0.52
    AccessorTable
    0.49
     kaj
    0.44
     McKnight
    0.43
    vant
    0.42
    annister
    0.42
     Vann
    0.42
    oquia
    0.41
     khai
    0.40
    EXPRESSION
    0.40
    Activations Density 0.854%

    No Known Activations