© 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. 4578
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation in the code, especially periods, parentheses, equals, and underscores, as well as numbers

    oai_token-act-pair · gemini-2.0-flash

    words with archaic or stylized spelling

    np_token-act-pair-logits · gpt-4o-mini
    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
     the
    -1.02
     N
    -0.97
     
    -0.97
     de
    -0.94
     v
    -0.94
     n
    -0.94
     di
    -0.94
     d
    -0.93
     R
    -0.90
     (
    -0.90
    POSITIVE LOGITS
     itſelf
    1.73
     myſelf
    1.47
     Monfieur
    1.41
     Theſe
    1.39
     Majefty
    1.38
     pleaſure
    1.37
     ་་
    1.35
     Reſ
    1.30
     doubtnut
    1.30
     poffible
    1.30
    Activations Density 4.232%

    No Known Activations