© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166405
    Prev
    Next
    INDEX
    Explanations

    fractal subdivision

    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_31_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
    돌
    0.33
     recruiter
    0.32
     kontakt
    0.31
     tolerate
    0.31
    接触
    0.31
     unprofessional
    0.31
     Watershed
    0.31
    TypeError
    0.31
     binoculars
    0.30
     Cro
    0.30
    POSITIVE LOGITS
     शिखर
    0.32
    केंद्रीय
    0.31
    殿
    0.31
     نتكلم
    0.31
    batches
    0.30
    MASTER
    0.30
    ABLISHED
    0.30
    ﻢ
    0.30
    ५
    0.29
    பசு
    0.29
    Activations Density 0.004%

    No Known Activations