© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154729
    Prev
    Next
    INDEX
    Explanations

    AEG

    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_60_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
     as
    0.52
     i
    0.48
     heater
    0.46
     amusement
    0.46
     wired
    0.45
     y
    0.44
     wonderful
    0.44
     missed
    0.44
     auditory
    0.43
     a
    0.42
    POSITIVE LOGITS
     Aeg
    0.98
     Æ
    0.81
     aeg
    0.79
     AEG
    0.78
     AE
    0.77
     Ae
    0.77
     Hae
    0.72
    Ae
    0.71
    Æ
    0.71
    AE
    0.69
    Activations Density 0.001%

    No Known Activations