© 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. 15384
    Prev
    Next
    INDEX
    Explanations

    the word "pretty"

    oai_token-act-pair · gemini-2.0-flash

    the word 'pretty'

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

    pretty

    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
     समीक्षक
    -0.51
     transfieras
    -0.45
    ngOnInit
    -0.44
    SuppressMessage
    -0.43
     Signalez
    -0.40
     nevoie
    -0.39
     sopr
    -0.39
     votos
    -0.38
    dart
    -0.38
    NamedQueries
    -0.38
    POSITIVE LOGITS
     much
    1.14
    much
    1.05
     Much
    1.01
    Much
    1.00
     MUCH
    0.80
     Efq
    0.78
    TagHelper
    0.73
     مشين
    0.72
    jspx
    0.68
     mucho
    0.67
    Activations Density 0.419%

    No Known Activations