© 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. 12940
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and religious texts

    oai_token-act-pair · gemini-2.0-flash

    the word 'given' and related small words

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

    Math/science theorem proofs

    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
     Monfieur
    -0.97
     itſelf
    -0.93
     Jefus
    -0.93
     iſt
    -0.89
     purpoſe
    -0.89
     pleaſure
    -0.86
     myſelf
    -0.86
     ainfi
    -0.86
     uſe
    -0.84
    الحياه
    -0.81
    POSITIVE LOGITS
     given
    0.67
     due
    0.64
     re
    0.53
    given
    0.51
     g
    0.50
     Given
    0.49
     
    0.49
     Rec
    0.48
     K
    0.47
     no
    0.47
    Activations Density 4.207%

    No Known Activations