© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4492
    Prev
    Next
    INDEX
    Explanations

    numbers or words associated with counting

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    three
    -1.28
     three
    -1.20
    five
    -1.17
    six
    -1.16
     five
    -1.13
     four
    -1.13
    Three
    -1.13
    four
    -1.10
     six
    -1.08
     trois
    -1.06
    POSITIVE LOGITS
    NOPQRST
    0.72
     Meksiku
    0.67
     BoxFit
    0.65
    mybatisplus
    0.65
    enumii
    0.60
    ItemBackground
    0.57
    hlands
    0.57
    errHandler
    0.56
    ịp
    0.56
    SequentialGroup
    0.55
    Activations Density 5.871%

    No Known Activations