© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11643
    Prev
    Next
    INDEX
    Explanations

    words related to opinions, disagreements, and discourse

    oai_token-act-pair · gemini-2.0-flash

    words related to opinions and perspectives

    np_token-act-pair-logits · gpt-4o-mini

    opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    adaptiveStyles
    -0.82
     derro
    -0.60
     kader
    -0.55
    onatos
    -0.54
     decret
    -0.50
     TextAppearance
    -0.50
    igable
    -0.50
     "..\..\
    -0.50
    focal
    -0.49
    aerial
    -0.49
    POSITIVE LOGITS
    الإنجليزية
    0.58
    +#+#
    0.57
     Trouver
    0.56
     InputDecoration
    0.53
    ">:
    0.52
    InstrumentedTest
    0.52
    awtextra
    0.52
    ゴリー
    0.51
     BorderRadius
    0.50
    ρισσότε
    0.49
    Activations Density 6.245%

    No Known Activations