© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37024
    Prev
    Next
    INDEX
    Explanations

    soft, perfectly, incredibly, really

    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
    Negative Logits
    タリア
    0.37
    Crit
    0.37
    ],\
    0.37
     happens
    0.35
     felt
    0.34
    iop
    0.34
     সিদ্দিক
    0.34
    ারে
    0.34
    iro
    0.34
     river
    0.34
    POSITIVE LOGITS
    棒
    0.39
    उट
    0.39
    साना
    0.38
    вт
    0.37
     sooo
    0.37
    
    0.37
    Magnet
    0.37
    ╋
    0.37
     onPress
    0.36
    anceled
    0.36
    Activations Density 0.005%

    No Known Activations