© 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. 12303
    Prev
    Next
    INDEX
    Explanations

    statistics related to change

    oai_token-act-pair · gemini-2.0-flash

    the word "since"

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

    since

    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
     oprot
    -0.50
    ciclop
    -0.49
     तक
    -0.48
    hasPermission
    -0.47
    NameInMap
    -0.46
    까지
    -0.46
     heb
    -0.45
    kyou
    -0.44
    までの
    -0.44
    まで
    -0.44
    POSITIVE LOGITS
     since
    1.97
    since
    1.80
     SINCE
    1.70
     Since
    1.52
    Since
    1.47
     fince
    1.40
     depuis
    1.36
     seit
    1.20
     sejak
    1.19
     Depuis
    1.15
    Activations Density 3.631%

    No Known Activations