© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2955
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    Single digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pleaſure
    -0.87
     purpoſe
    -0.81
     reaſon
    -0.79
     quæ
    -0.78
     Monfieur
    -0.77
     ſeveral
    -0.75
     ſtate
    -0.74
     ſmall
    -0.73
     greateſt
    -0.73
     république
    -0.73
    POSITIVE LOGITS
    LookAnd
    0.63
    marshaller
    0.61
     ins
    0.60
     ISNI
    0.59
    ửa
    0.56
     the
    0.55
     c
    0.54
    ClCompile
    0.54
     estekak
    0.54
     <=",
    0.54
    Activations Density 7.079%

    No Known Activations