© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237174
    Prev
    Next
    INDEX
    Explanations

    paste

    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_46_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
    }=\{
    0.39
     contexte
    0.38
    irce
    0.38
    ниципа
    0.37
    aimanapun
    0.37
    arrant
    0.36
     Cots
    0.36
    𝕟
    0.36
    ТС
    0.35
    टीएस
    0.35
    POSITIVE LOGITS
     unlimited
    0.46
     bid
    0.39
    Bid
    0.39
    Unlimited
    0.38
     bidirectional
    0.38
     अनलिमिटेड
    0.37
     Bid
    0.36
    挡
    0.36
     Unlimited
    0.36
    ulfonic
    0.35
    Activations Density 0.005%

    No Known Activations