© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171167
    Prev
    Next
    INDEX
    Explanations

    really

    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
    Negative Logits
     trial
    0.41
     ”
    0.39
    无
    0.39
     Past
    0.38
     False
    0.38
    सूत्र
    0.38
     Library
    0.37
     tangle
    0.37
     Repar
    0.37
    탐
    0.37
    POSITIVE LOGITS
    speaking
    0.50
    too
    0.50
     речь
    0.48
     berbicara
    0.47
     sprechen
    0.46
    speak
    0.44
     слишком
    0.40
     gesprochen
    0.39
     falam
    0.39
     speak
    0.38
    Activations Density 0.000%

    No Known Activations