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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10850
    Prev
    Next
    INDEX
    Explanations

    numbers, especially percentages or other statistics with decimals

    oai_token-act-pair · gemini-2.0-flash

    numbers and measurements

    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
    ^(@)
    -1.02
    sizeCache
    -0.97
    matchCondition
    -0.88
    leſs
    -0.88
     himſelf
    -0.86
     Jefus
    -0.85
     myſelf
    -0.85
     raiſ
    -0.83
    Referanser
    -0.83
     itſelf
    -0.83
    POSITIVE LOGITS
    7
    0.58
    9
    0.57
    -
    0.52
    O
    0.51
    5
    0.45
    8
    0.45
    6
    0.44
    4
    0.44
    D
    0.44
    .
    0.43
    Activations Density 11.562%

    No Known Activations