© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138177
    Prev
    Next
    INDEX
    Explanations

    lifetimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sn
    0.44
     Cele
    0.43
     düşün
    0.38
     Alerts
    0.37
    Sn
    0.37
     Alert
    0.36
     celebs
    0.36
    ">=
    0.35
     Celebr
    0.35
     type
    0.34
    POSITIVE LOGITS
     belly
    0.41
    timestep
    0.39
    希望
    0.38
     lifetime
    0.38
     lifetimes
    0.38
    aving
    0.37
    enser
    0.36
    anqu
    0.35
     मनीष
    0.35
    手中
    0.35
    Activations Density 0.001%

    No Known Activations