© 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. 12132
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is" contracted to "'s" or "'re" or "&".

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "be"

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

    s

    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
    ponses
    -0.48
     उन्होंने
    -0.42
    appearing
    -0.41
    愁
    -0.40
     उसने
    -0.40
    пису
    -0.40
    envolvimento
    -0.39
    がる
    -0.39
    ops
    -0.38
    sieht
    -0.38
    POSITIVE LOGITS
     been
    2.03
     gotten
    1.73
    been
    1.66
     gone
    1.61
     BEEN
    1.47
    Been
    1.38
     Been
    1.36
    gotten
    1.35
     arisen
    1.34
     undergone
    1.32
    Activations Density 0.825%

    No Known Activations