© 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. 2963
    Prev
    Next
    INDEX
    Explanations

    words that suggest comparisons or several things

    oai_token-act-pair · gemini-2.0-flash

    listing details

    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
    many
    -1.33
     many
    -1.31
    Many
    -1.13
     Many
    -1.10
    MANY
    -1.06
     MANY
    -1.05
     nombreuses
    -1.01
     molte
    -1.01
     muchos
    -1.00
    Numerous
    -1.00
    POSITIVE LOGITS
    Revenir
    0.48
    tvguidetime
    0.41
     credits
    0.41
    bul
    0.40
    formik
    0.39
    נון
    0.39
    DatabaseError
    0.38
    cemia
    0.38
    不觉
    0.38
     ومل
    0.37
    Activations Density 2.178%

    No Known Activations