© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11969
    Prev
    Next
    INDEX
    Explanations

    numbers, especially dollar amounts, population counts, and statistics

    oai_token-act-pair · gemini-2.0-flash

    single-digit numbers

    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
    LookAnd
    -0.98
    AndEndTag
    -0.95
    berdayakan
    -0.90
     Theſe
    -0.89
    elemField
    -0.88
     kasarigan
    -0.86
     Efq
    -0.85
     myſelf
    -0.80
     disponibilités
    -0.76
     المعيارى
    -0.76
    POSITIVE LOGITS
    0
    0.63
    9
    0.55
    4
    0.53
    3
    0.52
    os
    0.52
    5
    0.52
    6
    0.51
    7
    0.48
     ско
    0.48
    8
    0.48
    Activations Density 4.023%

    No Known Activations