© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3378
    Prev
    Next
    INDEX
    Explanations

    words/phrases in Spanish, Portuguese, and possibly other Romance languages

    oai_token-act-pair · gemini-2.0-flash

    Code and Latin American topics

    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
    ViewFeatures
    -0.66
    醐
    -0.64
     SwitchCompat
    -0.62
    SuccessListener
    -0.61
    yaf
    -0.59
    gway
    -0.58
    راسیون
    -0.58
    antart
    -0.57
    ieux
    -0.57
     Réponses
    -0.56
    POSITIVE LOGITS
    #![
    0.42
     braccio
    0.42
    Amir
    0.39
    numerusform
    0.38
     claim
    0.37
     pescoço
    0.37
    świad
    0.36
     Mention
    0.36
    oció
    0.36
    claims
    0.35
    Activations Density 1.161%

    No Known Activations