© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3041
    Prev
    Next
    INDEX
    Explanations

    a mix of Facebook terms, words related to system errors, and characters from different alphabets

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    enumi
    -0.59
    يون
    -0.49
     חיצוניים
    -0.47
    coccal
    -0.47
    noční
    -0.47
     Addams
    -0.44
    ativit
    -0.44
    命名
    -0.44
    ocera
    -0.44
    Jem
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.81
     nahilalakip
    0.73
    zego
    0.70
    owego
    0.70
    ного
    0.69
    neho
    0.66
    UrlResolution
    0.66
     resourceCulture
    0.66
    ního
    0.66
    нного
    0.64
    Activations Density 0.569%

    No Known Activations