© 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. 16354
    Prev
    Next
    INDEX
    Explanations

    phrases that express an opinion or approval

    oai_token-act-pair · gemini-2.0-flash

    opinions in discussion

    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
    Negative Logits
     contextLoads
    -0.51
    олові
    -0.49
    GraphicsUnit
    -0.49
    ellschaft
    -0.49
     giochi
    -0.46
     Initialized
    -0.46
    asable
    -0.46
    thenReturn
    -0.46
    lapsed
    -0.46
    Билгалдахарш
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.72
    migrationBuilder
    0.69
     gradova
    0.63
    abestanden
    0.62
    HasForeignKey
    0.61
     JpaRepository
    0.61
    adaptiveStyles
    0.57
     typelib
    0.57
    rrggbb
    0.56
     يتيمه
    0.56
    Activations Density 2.021%

    No Known Activations