© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7973
    Prev
    Next
    INDEX
    Explanations

    uses of the word "guarantee" and related abstract nouns.

    oai_token-act-pair · gemini-2.0-flash

    guarantee

    np_max-act · gemini-2.0-flash
    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
     the
    -1.07
     
    -0.89
    <strong>
    -0.89
    <b>
    -0.80
     a
    -0.74
    <em>
    -0.72
    y
    -0.72
     all
    -0.71
    …
    -0.71
    The
    -0.67
    POSITIVE LOGITS
     kasarigan
    1.59
    TagMode
    1.54
    
    1.50
     autorytatywna
    1.48
    rungsseite
    1.42
     <=",
    1.38
     Roskov
    1.36
    ⓧ
    1.36
    Portale
    1.34
    OGND
    1.33
    Activations Density 1.915%

    No Known Activations