© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12200
    Prev
    Next
    INDEX
    Explanations

    a variety of specific nouns

    oai_token-act-pair · gemini-2.0-flash

    Scientific studies and research

    np_max-act · gemini-2.0-flash

    say "▁"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    •hello_world:278c2a25-8446-5049-a239-c74419102559
    Top frequency features for prompt

    No Comments

    Negative Logits
    <bos>
    -2.30
    '
    -1.11
     
    -0.96
    ’
    -0.89
    ↵
    -0.87
    The
    -0.86
      
    -0.85
    ↵↵
    -0.84
    2
    -0.81
     the
    -0.81
    POSITIVE LOGITS
    ^(@)
    1.19
     Efq
    1.16
     myſelf
    1.09
     doubtnut
    1.08
     ―――――
    1.07
     Majefty
    1.04
     iſt
    1.02
     purpoſe
    1.02
     Jefus
    1.01
     $_"
    1.01
    Activations Density 13.759%

    No Known Activations