© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193268
    Prev
    Next
    INDEX
    Explanations

    called X

    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_27_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
    histoire
    0.31
     interessant
    0.30
    @"
    0.30
    PROBLE
    0.30
     architet
    0.29
    blog
    0.29
    tor
    0.29
     ستر
    0.29
    knee
    0.29
     ಮಾತನಾಡ
    0.29
    POSITIVE LOGITS
    ،
    0.30
     değ
    0.30
    γωγ
    0.30
     vitt
    0.29
    ,
    0.29
    rodní
    0.28
     samp
    0.27
    τικό
    0.27
     IRL
    0.26
     jakim
    0.26
    Activations Density 0.009%

    No Known Activations