© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    the word "soft"

    oai_token-act-pair · gemini-2.0-flash

    soft

    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
    WebVitals
    -0.85
    sizeCache
    -0.84
    তথ্যসূত্র
    -0.84
    sidemargin
    -0.81
     FormGroup
    -0.80
     ujednoznacz
    -0.80
    تقاوى
    -0.79
     Xunit
    -0.79
     BrowserModule
    -0.79
    下载附件
    -0.79
    POSITIVE LOGITS
    <bos>
    0.49
    袱
    0.48
    But
    0.47
     الشرق
    0.47
    Make
    0.47
     pinulongan
    0.46
    FONT
    0.46
    past
    0.45
     rés
    0.45
    forts
    0.44
    Activations Density 0.260%

    No Known Activations