© 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. 169580
    Prev
    Next
    INDEX
    Explanations

    ancient times

    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
    `]
    0.37
    جے
    0.35
     ዋና
    0.33
    】-
    0.33
    튼
    0.33
    దం
    0.33
     nachdem
    0.32
     pärast
    0.32
     millennials
    0.32
    IGE
    0.32
    POSITIVE LOGITS
     childhood
    1.22
     ancient
    1.17
     древ
    1.04
    ancient
    1.04
    古
    0.97
     Childhood
    0.97
    Ancient
    0.88
     boyhood
    0.88
     Ancient
    0.87
     prehistoric
    0.84
    Activations Density 0.002%

    No Known Activations