© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3227
    Prev
    Next
    INDEX
    Explanations

    the word "living" with some temporal context

    oai_token-act-pair · gemini-2.0-flash

    living

    np_max-act · gemini-2.0-flash

    living

    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
     виправивши
    -0.82
    LLocation
    -0.82
    expandindo
    -0.79
    ſelf
    -0.77
    kháu
    -0.76
    ſelves
    -0.75
     محفوظة
    -0.74
    CppMethod
    -0.73
    zzleHttp
    -0.73
     $_(
    -0.73
    POSITIVE LOGITS
    ↵
    0.79
    I
    0.74
     pretty
    0.58
    <eos>
    0.56
    </h3>
    0.55
    二是
    0.55
    ↵↵
    0.54
    </i>
    0.54
     I
    0.54
    The
    0.52
    Activations Density 0.669%

    No Known Activations