© 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. 7297
    Prev
    Next
    INDEX
    Explanations

    a complex combination of negative feelings, actions taken, and team sports

    oai_token-act-pair · gemini-2.0-flash

    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_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
    醐
    -0.65
    himself
    -0.61
     Meksiku
    -0.59
    BeginContext
    -0.59
    /**
    -0.57
    ajiban
    -0.54
    LookAnd
    -0.54
    herself
    -0.53
    SuppressMessage
    -0.52
    ۜ
    -0.52
    POSITIVE LOGITS
     your
    1.59
     seu
    1.45
     their
    1.45
     seus
    1.42
     my
    1.42
     sua
    1.41
     its
    1.38
     his
    1.35
     our
    1.28
     suas
    1.23
    Activations Density 2.674%

    No Known Activations