© 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. 15352
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey positive sentiment or desires

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives related to quality

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

    good

    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
    oredCriteria
    -0.60
    GeneratedMessage
    -0.59
    OGND
    -0.57
    InvalidProtocol
    -0.57
     kaarangay
    -0.56
    IVEREF
    -0.55
    Tikang
    -0.54
     mergeFrom
    -0.54
    oa̍t
    -0.53
    lapsingToolbar
    -0.52
    POSITIVE LOGITS
     good
    1.19
     best
    1.09
     excellent
    1.06
     terbaik
    1.01
     better
    1.00
     mejor
    0.99
     tốt
    0.98
     mejores
    0.96
     meilleur
    0.96
    excellent
    0.95
    Activations Density 1.232%

    No Known Activations