© 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. 13014
    Prev
    Next
    INDEX
    Explanations

    common and function words ("the", "in", "and", "or", "they", "their", etc.) that often act as connectors within sentences

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    np_max-act · gemini-2.0-flash

    they

    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
     arşivlendi
    -1.09
     ComVisible
    -1.03
    ValueStyle
    -1.02
     HasFactory
    -1.01
    IsContent
    -0.99
    GenerationType
    -0.98
     gynhyrchwyd
    -0.96
    basicConfig
    -0.96
     الرياضيه
    -0.93
    twimg
    -0.93
    POSITIVE LOGITS
    ↵
    0.83
    ,
    0.74
    .
    0.70
    </h5>
    0.62
    </u>
    0.55
    ↵↵
    0.53
    <eos>
    0.50
    "](
    0.48
    ↵↵↵
    0.47
    k
    0.47
    Activations Density 25.217%

    No Known Activations