© 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. 1782
    Prev
    Next
    INDEX
    Explanations

    language related to scenarios with a winner and a loser

    oai_token-act-pair · gemini-2.0-flash

    losing/risk situations

    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
     lost
    -2.77
    lost
    -2.44
     Lost
    -2.33
    Lost
    -2.30
     LOST
    -2.08
     loss
    -1.91
     perdido
    -1.86
    LOST
    -1.77
     Loss
    -1.77
    Loss
    -1.74
    POSITIVE LOGITS
    SourceChecksum
    0.65
     autorytatywna
    0.63
     ujednoznacz
    0.61
    MessageTagHelper
    0.58
    skap
    0.54
    HasBeenSet
    0.52
    sizeCache
    0.50
     дописавши
    0.49
    rilled
    0.47
    utze
    0.47
    Activations Density 3.114%

    No Known Activations