© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    phrases related to losing something, often in the context of abstract concepts

    oai_token-act-pair · gemini-2.0-flash

    lose

    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
    -0.84
    loss
    -0.79
    Loss
    -0.76
     LOSS
    -0.75
     loss
    -0.72
    lost
    -0.71
     Loss
    -0.70
     pérdida
    -0.68
     perte
    -0.66
     lose
    -0.66
    POSITIVE LOGITS
     Normdatei
    0.79
    sizeCache
    0.79
     AssemblyVersion
    0.72
    contentLoaded
    0.70
    $.
    0.67
    ClientSize
    0.63
    ]")]
    0.61
    djangoproject
    0.61
    InjectAttribute
    0.60
     MainAxisSize
    0.60
    Activations Density 6.740%

    No Known Activations