© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208426
    Prev
    Next
    INDEX
    Explanations

    self

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     self
    0.74
    自
    0.70
     само
    0.66
     training
    0.59
     TRAINING
    0.57
     SELF
    0.57
     zelf
    0.52
     tự
    0.52
     selbst
    0.52
     自
    0.52
    POSITIVE LOGITS
     Employ
    0.49
    helper
    0.42
    ialize
    0.42
     Dependencies
    0.42
    statistic
    0.41
    辩
    0.41
    employer
    0.41
    employ
    0.41
     Verteid
    0.40
     employé
    0.39
    Activations Density 0.001%

    No Known Activations