© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11507
    Prev
    Next
    INDEX
    Explanations

    references to conflict or competition

    oai_token-act-pair · gemini-2.0-flash

    Butt

    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
     dick
    -0.73
     cock
    -0.70
     ass
    -0.68
     Hermans
    -0.57
    dick
    -0.50
     asses
    -0.49
     tits
    -0.48
     DICK
    -0.48
     pussy
    -0.48
     ITC
    -0.46
    POSITIVE LOGITS
     behind
    0.83
     bottom
    0.81
    behind
    0.78
    原始内容存档于
    0.74
    bottom
    0.73
     Bottom
    0.71
    Behind
    0.71
     BEHIND
    0.71
     BOTTOM
    0.69
     rear
    0.69
    Activations Density 2.629%

    No Known Activations