© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242218
    Prev
    Next
    INDEX
    Explanations

    number of years elapsed

    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_40_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
    ules
    0.40
    umma
    0.40
    -...
    0.38
    νων
    0.38
    ajn
    0.37
    ysen
    0.37
    ெல்ல
    0.36
    nsic
    0.36
    utal
    0.36
    innaker
    0.35
    POSITIVE LOGITS
     autrefois
    0.44
    stderr
    0.40
     repertoire
    0.38
    郷
    0.38
     Astrology
    0.37
     Repair
    0.37
     sửa
    0.37
    Repair
    0.37
    壽
    0.37
    ソース
    0.37
    Activations Density 0.004%

    No Known Activations