© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7985
    Prev
    Next
    INDEX
    Explanations

    negative opinions of people

    oai_token-act-pair · gemini-2.0-flash

    negative/hateful speech

    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
     المعيارى
    -0.70
    writeField
    -0.66
    athione
    -0.56
     Addressing
    -0.54
     الحره
    -0.54
     kasarigan
    -0.54
     asin
    -0.52
    contentLoaded
    -0.52
     fadeIn
    -0.52
    AddField
    -0.52
    POSITIVE LOGITS
     يتيمه
    0.61
    httphttps
    0.54
    unknownFields
    0.53
    monių
    0.50
    
    0.47
     choses
    0.47
    principalTable
    0.44
    @[+][
    0.43
    MODE
    0.43
    ukkig
    0.43
    Activations Density 9.842%

    No Known Activations