© 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. 6061
    Prev
    Next
    INDEX
    Explanations

    terms in a non-English language related to agreements, rules, or verification, possibly in the context of a Facebook app

    oai_token-act-pair · gemini-2.0-flash

    Translations

    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
    PreInfinity
    -0.52
     näh
    -0.51
    rungsseite
    -0.50
     holt
    -0.49
     صوتيه
    -0.48
     vacanze
    -0.47
     défaut
    -0.46
     goles
    -0.45
     olet
    -0.44
     adım
    -0.43
    POSITIVE LOGITS
    ">—
    0.75
    ⓧ
    0.72
    Tembelea
    0.69
     '\\;'
    0.62
     lenker
    0.60
    findpost
    0.59
     nahilalakip
    0.59
     TestBed
    0.57
     Réponses
    0.56
    Vidite
    0.55
    Activations Density 0.820%

    No Known Activations