© 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. 12566
    Prev
    Next
    INDEX
    Explanations

    language related to court rulings

    oai_token-act-pair · gemini-2.0-flash

    affirmed

    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
     Keys
    -0.44
    Keys
    -0.43
     van
    -0.42
    ‍
    -0.41
     procurer
    -0.41
    გ
    -0.41
     утвер
    -0.40
     раз
    -0.40
     Corporation
    -0.40
    oney
    -0.40
    POSITIVE LOGITS
     مشين
    0.94
     unknownFields
    0.88
    tagHelperRunner
    0.85
     snippetHide
    0.81
    RenderAtEndOf
    0.80
    expandindo
    0.77
    HasForeignKey
    0.75
    LookAnd
    0.75
    StoryboardSegue
    0.73
    ConstraintMaker
    0.71
    Activations Density 5.820%

    No Known Activations