© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3229
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hat" and shortened words, such as "can't" to "cant"

    oai_token-act-pair · gemini-2.0-flash

    hat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ality
    -0.60
    rungsseite
    -0.58
     Lightboxes
    -0.57
     hier
    -0.56
    localctx
    -0.54
     فريبيس
    -0.53
    дравству
    -0.51
    t
    -0.51
    tten
    -0.51
    er
    -0.51
    POSITIVE LOGITS
     fotografico
    0.83
    ostante
    0.82
    seamnă
    0.81
     AIAA
    0.78
     découver
    0.78
     fallu
    0.77
     animés
    0.77
     médicaux
    0.77
     africains
    0.77
     positifs
    0.76
    Activations Density 3.225%

    No Known Activations