© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    contractions and slang

    oai_token-act-pair · gemini-2.0-flash

    conversational filler

    np_max-act · gemini-2.0-flash

    say "apostrophe"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     الحره
    -1.09
     المعيارى
    -1.05
    +#+#
    -1.05
    EDEFAULT
    -1.02
     CreateTagHelper
    -0.98
     سكانية
    -0.98
     snippetHide
    -0.97
    TagMode
    -0.95
     Мексичка
    -0.93
    ftagPool
    -0.92
    POSITIVE LOGITS
     The
    0.59
    ↵
    0.57
    '
    0.54
    ↵↵
    0.54
     
    0.51
    </strong>
    0.49
     in
    0.48
    !
    0.48
     on
    0.47
    ,
    0.47
    Activations Density 10.136%

    No Known Activations