© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10659
    Prev
    Next
    INDEX
    Explanations

    the pronouns "it," "them," in the context of "all" and some helping verbs.

    oai_token-act-pair · gemini-2.0-flash

    the word 'all'

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

    all

    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
     it
    -0.63
     кӀ
    -0.61
     actionMode
    -0.52
     vPvB
    -0.52
    elemField
    -0.52
    CodeAttribute
    -0.51
    /**
    -0.50
     "..\..\..\
    -0.49
    roek
    -0.49
    thalene
    -0.48
    POSITIVE LOGITS
     all
    2.75
    all
    2.08
     ALL
    1.79
     semua
    1.76
     allemaal
    1.75
     всех
    1.59
    All
    1.51
     All
    1.46
    ALL
    1.45
     wszystkich
    1.45
    Activations Density 1.329%

    No Known Activations