© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3828
    Prev
    Next
    INDEX
    Explanations

    the word 'friendly'

    oai_token-act-pair · gemini-2.0-flash

    friendly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     friendly
    -2.56
    friendly
    -2.25
     Friendly
    -2.23
    Friendly
    -2.22
     friendliness
    -1.76
     unfriendly
    -1.36
     FRIEND
    -1.36
     vriende
    -1.34
    FRIEND
    -1.24
     freundlich
    -1.20
    POSITIVE LOGITS
    клопе
    0.81
     excru
    0.63
    тьяна
    0.61
     nakalista
    0.61
    InjectAttribute
    0.60
    Хьажоргаш
    0.59
    ########.
    0.59
    IConfiguration
    0.57
     nî
    0.57
    Rüyada
    0.57
    Activations Density 1.275%

    No Known Activations