© 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. 143677
    Prev
    Next
    INDEX
    Explanations

    mental

    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
     ദൈ
    0.41
    ǿ
    0.39
    aseña
    0.38
     architecture
    0.37
    stände
    0.37
    헉
    0.37
    éristique
    0.37
    asek
    0.37
    ையோ
    0.36
     Oro
    0.36
    POSITIVE LOGITS
    질
    0.46
    ilangkan
    0.40
    㥉
    0.39
    RPC
    0.39
     Gru
    0.37
     Logistics
    0.37
    ivan
    0.36
     gru
    0.36
    gru
    0.35
     combin
    0.35
    Activations Density 0.002%

    No Known Activations