© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12518
    Prev
    Next
    INDEX
    Explanations

    concepts relating to health, both mental and physical, and electricity

    oai_token-act-pair · gemini-2.0-flash

    law or electromagnetism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ArgsConstructor
    -0.53
    ције
    -0.52
    InputTagHelper
    -0.49
    tagHelperRunner
    -0.48
    ariConfig
    -0.48
     avantaj
    -0.47
     verm
    -0.46
    JsonInclude
    -0.46
    Itinerary
    -0.46
    RUnlock
    -0.45
    POSITIVE LOGITS
     ExecuteAsync
    0.60
    MENAFN
    0.60
    الحياه
    0.59
    culoskeletal
    0.57
    delli
    0.56
     GenerationType
    0.55
    ‍♀
    0.54
    osocial
    0.54
    Referencies
    0.53
    HomeAsUpEnabled
    0.52
    Activations Density 4.467%

    No Known Activations