© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2568
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty with words like "certainly," "not," or negative contractions.

    oai_token-act-pair · gemini-2.0-flash

    Certainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rungsseite
    -0.85
    تفصیلات
    -0.77
     EconPapers
    -0.77
    Geplaatst
    -0.75
    脚注の使い方
    -0.73
     HasFactory
    -0.73
    sizeCache
    -0.72
     समीक्षक
    -0.71
    enterOuterAlt
    -0.71
    TargetException
    -0.71
    POSITIVE LOGITS
    <bos>
    0.56
    
    0.48
     clear
    0.42
     adults
    0.42
     adult
    0.41
     Haush
    0.40
     majority
    0.40
    Clearly
    0.39
     Clear
    0.39
    显然
    0.39
    Activations Density 1.760%

    No Known Activations