© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and emotional arguments or foreign cultures

    oai_token-act-pair · gemini-2.0-flash

    superhuman

    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
    ItemBackground
    -0.60
    AddTagHelper
    -0.57
    InputTagHelper
    -0.56
     виправивши
    -0.55
     conditioned
    -0.52
    Doi
    -0.52
     Jolly
    -0.52
    wery
    -0.51
     &
    -0.51
    arcoma
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.73
    
    0.69
    })*/
    0.55
    siąż
    0.52
    "])
    0.52
     Witkin
    0.50
    MENAFN
    0.50
    "?>
    0.48
    })));
    0.48
    ngdoc
    0.47
    Activations Density 5.345%

    No Known Activations