© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15608
    Prev
    Next
    INDEX
    Explanations

    a mix of function words (conjunctions, prepositions, pronouns), action words, and words indicating something that *has* something else

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_token-act-pair-logits · gpt-4o-mini

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    SerializedName
    -0.56
    addCriterion
    -0.55
    setViewName
    -0.53
    ortun
    -0.53
    atería
    -0.52
    OURS
    -0.52
    thâu
    -0.50
    Siblings
    -0.50
    ztal
    -0.50
    heu
    -0.50
    POSITIVE LOGITS
     its
    2.14
    its
    1.53
    Its
    1.52
     Its
    1.45
    其
    1.37
     seus
    1.32
     their
    1.30
     suas
    1.28
     sua
    1.25
     seu
    1.23
    Activations Density 6.692%

    No Known Activations