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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3161
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to professions and expertise, in fields ranging from business to medicine to education.

    oai_token-act-pair · 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
     offer
    -0.60
     set
    -0.60
     verify
    -0.58
     help
    -0.50
     cater
    -0.49
     deal
    -0.48
    最
    -0.48
     charge
    -0.48
     Offer
    -0.48
     protect
    -0.47
    POSITIVE LOGITS
     typelib
    0.84
    出版年
    0.75
     utafitiHapana
    0.74
    SuppressLint
    0.69
    mybatisplus
    0.68
     dramatique
    0.66
     transfieras
    0.65
    IUrlHelper
    0.65
     stratégique
    0.65
    RTDA
    0.63
    Activations Density 3.288%

    No Known Activations