© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5020
    Prev
    Next
    INDEX
    Explanations

    the word "Ren" followed by various suffixes/endings

    oai_token-act-pair · gemini-2.0-flash

    references to "Renormalization"

    np_token-act-pair-logits · gpt-4o-mini

    Ren

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     createState
    -0.72
     BorderRadius
    -0.63
    CloseOperation
    -0.56
     EdgeInsets
    -0.53
     cref
    -0.49
    RequiresApi
    -0.49
     slide
    -0.48
    esModule
    -0.48
     HttpHeaders
    -0.47
    تقاوى
    -0.46
    POSITIVE LOGITS
     ſtate
    0.65
     againſt
    0.62
     poffible
    0.61
     pleaſure
    0.60
    Referanser
    0.58
     ftate
    0.57
     juſt
    0.57
     ſeveral
    0.56
     Jefus
    0.56
     ſta
    0.56
    Activations Density 0.646%

    No Known Activations