© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    words that contribute to the tone of the piece, such as negative words, but also words related to books or writing.

    oai_token-act-pair · gemini-2.0-flash

    turns

    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
    kháu
    -0.90
     BoxFit
    -0.72
     protoimpl
    -0.71
     الحره
    -0.69
    +#+#
    -0.68
     Савезне
    -0.68
     تضيفلها
    -0.68
     referenties
    -0.67
    __':
    -0.66
    Jereo
    -0.63
    POSITIVE LOGITS
    heureusement
    0.66
    ifolia
    0.53
     hierbei
    0.50
     perna
    0.49
     Tieren
    0.48
      
    0.47
     bông
    0.47
     &___
    0.46
    liet
    0.46
     INCOR
    0.46
    Activations Density 7.440%

    No Known Activations