© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "us", "we", and words related to collective actions

    oai_token-act-pair · gemini-2.0-flash

    us/all

    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
    脚注の使い方
    -0.89
     المعيارى
    -0.88
     Wikimedijinoj
    -0.75
    Personendaten
    -0.75
    gonia
    -0.73
    AddTagHelper
    -0.72
     utafitiHapana
    -0.71
    RegistryLite
    -0.71
    StoreMessageInfo
    -0.70
    expandindo
    -0.69
    POSITIVE LOGITS
    agg
    0.44
     Himmel
    0.40
     us
    0.39
    เห็น
    0.39
     who
    0.38
    abond
    0.37
     aufge
    0.37
    lay
    0.37
    ple
    0.36
     living
    0.35
    Activations Density 1.552%

    No Known Activations