© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6867
    Prev
    Next
    INDEX
    Explanations

    words referring to Muslims and Mormons, possibly religious references, but also picks up "mufti" and "ust" from context

    oai_token-act-pair · gemini-2.0-flash

    Sociopolitical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     propOrder
    -0.71
    verwijspagina
    -0.69
     defaultstate
    -0.65
     חיצוניים
    -0.63
    ]")]
    -0.62
     EconPapers
    -0.60
     كومونز
    -0.59
    labelledby
    -0.54
     "";
    -0.54
    '][]
    -0.53
    POSITIVE LOGITS
     Heaton
    0.60
     AppColors
    0.55
    PRESS
    0.52
     conversion
    0.52
     Bernadette
    0.52
     augen
    0.52
     Conversion
    0.52
    PLACEMENT
    0.50
    ileen
    0.50
     năng
    0.50
    Activations Density 0.425%

    No Known Activations