© 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. 15668
    Prev
    Next
    INDEX
    Explanations

    the word "tight" related to clothing or technical terms

    oai_token-act-pair · gemini-2.0-flash

    tight

    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
     tight
    -2.41
     Tight
    -2.41
    Tight
    -2.31
    tight
    -2.28
     tighter
    -2.19
     tighten
    -2.03
     tightened
    -1.93
     tightening
    -1.90
     tightness
    -1.73
     tightly
    -1.73
    POSITIVE LOGITS
    ⓧ
    0.50
     متعلقه
    0.47
    getStatusCode
    0.47
     Arend
    0.46
    チール
    0.46
     Soh
    0.43
     Oswald
    0.42
     Subsid
    0.42
    :✨
    0.42
     Coastal
    0.41
    Activations Density 4.178%

    No Known Activations