© 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. 1555
    Prev
    Next
    INDEX
    Explanations

    words related to Hindu worship

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms or complex words

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

    Narasimha

    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
     sp
    -0.43
    face
    -0.42
    sp
    -0.42
     ferons
    -0.42
    ars
    -0.42
     hombros
    -0.41
    ins
    -0.41
    pro
    -0.40
     ochi
    -0.40
    义
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.78
    ագրություններ
    0.68
    ſelves
    0.68
    rzez
    0.66
    abestanden
    0.64
    ViewFeatures
    0.64
    aticano
    0.63
     endwhile
    0.63
    auteuil
    0.61
     CreateTagHelper
    0.60
    Activations Density 0.225%

    No Known Activations