© 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. 14549
    Prev
    Next
    INDEX
    Explanations

    the word "bulk" and words indicating something negative

    oai_token-act-pair · gemini-2.0-flash

    negative tone

    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
     Anſ
    -0.84
     Оно
    -0.77
     Houſe
    -0.74
     itſelf
    -0.74
     giudi
    -0.73
     Theſe
    -0.73
       
    -0.72
     ་་
    -0.72
     ―――――
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
    æus
    0.68
    paddingVertical
    0.66
     Hoffmann
    0.65
    τητα
    0.63
    IKAN
    0.62
    s
    0.61
    流石
    0.61
     utilising
    0.60
     E
    0.60
     main
    0.60
    Activations Density 1.828%

    No Known Activations