© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 95
    Prev
    Next
    INDEX
    Explanations

    terms like "resort", "spa", "restaurants", and other things related to vacations, leisure, food, and travel.

    oai_token-act-pair · gemini-2.0-flash

    fire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     myſelf
    -0.97
    出版年
    -0.95
     faſt
    -0.93
     raiſ
    -0.93
     Monfieur
    -0.92
     Reſ
    -0.91
     purpoſe
    -0.91
     uſe
    -0.90
     hotel
    -0.88
     pleaſure
    -0.88
    POSITIVE LOGITS
    <eos>
    0.49
     
    0.44
     T
    0.44
     B
    0.42
     m
    0.42
     c
    0.41
    дец
    0.40
     tu
    0.40
    tu
    0.39
     D
    0.39
    Activations Density 4.293%

    No Known Activations