© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    discussions of burden of proof and evidence, often within legal contexts

    oai_token-act-pair · gemini-2.0-flash

    proof

    np_max-act · gemini-2.0-flash

    proof

    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
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -0.72
    e
    -0.68
    <b>
    -0.66
    eu
    -0.65
    S
    -0.64
    R
    -0.63
    ***
    -0.62
    E
    -0.62
    of
    -0.61
    得
    -0.61
    POSITIVE LOGITS
    GHIJKLM
    1.02
     Мексичка
    0.98
    ̈́
    0.93
    TagMode
    0.92
    endpush
    0.91
    çade
    0.91
    Personendaten
    0.88
    ValueStyle
    0.88
     onBackPressed
    0.87
    tvguidetime
    0.86
    Activations Density 3.528%

    No Known Activations