© 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. 11997
    Prev
    Next
    INDEX
    Explanations

    the word "it" or "IT", sometimes followed by another character

    oai_token-act-pair · gemini-2.0-flash

    instances of "It" and variations

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

    it

    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
     itſelf
    -1.23
     Monfieur
    -0.98
     myſelf
    -0.96
     themſelves
    -0.89
     purpoſe
    -0.88
     himſelf
    -0.87
     Theſe
    -0.87
     ſtate
    -0.85
     تانيه
    -0.85
    ſelves
    -0.84
    POSITIVE LOGITS
    вър
    0.53
     S
    0.53
     H
    0.51
     P
    0.51
    no
    0.50
     F
    0.49
     W
    0.48
     interesar
    0.48
     
    0.45
     la
    0.45
    Activations Density 0.657%

    No Known Activations