© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    the word "latter" along with surrounding text that specifies what "latter" is referring to.

    oai_token-act-pair · gemini-2.0-flash

    Comparisons, transitions

    np_max-act · gemini-2.0-flash

    latter

    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
    tvguidetime
    -1.36
    MigrationBuilder
    -0.96
     متعلقه
    -0.94
    WebVitals
    -0.90
     kasarigan
    -0.90
     Zacks
    -0.87
     resourceCulture
    -0.85
    :✨
    -0.80
     EconPapers
    -0.80
     مرئيه
    -0.78
    POSITIVE LOGITS
    <bos>
    2.03
    '
    1.02
    ’
    0.91
    ↵↵
    0.63
    ‘
    0.59
    ↵
    0.54
    </em>
    0.48
     
    0.46
    oczes
    0.46
    </strong>
    0.46
    Activations Density 22.674%

    No Known Activations