© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2651
    Prev
    Next
    INDEX
    Explanations

    words that indicate historical, racial, religious and/or political bias, with a negative sentiment.

    oai_token-act-pair · gemini-2.0-flash

    negative social commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     dislike
    -1.13
     hate
    -1.12
     complaints
    -1.10
     condemn
    -1.09
     criticized
    -1.07
     condemnation
    -1.07
     criticism
    -1.06
     hating
    -1.06
     rejection
    -1.04
     hatred
    -1.04
    POSITIVE LOGITS
     noDo
    0.67
     незавершена
    0.57
    DoubleQuotes
    0.55
    хьтан
    0.54
    rungsseite
    0.53
    uesia
    0.53
    StoryboardSegue
    0.52
     lo
    0.52
     consultato
    0.50
    EnableWeb
    0.50
    Activations Density 6.277%

    No Known Activations