© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137586
    Prev
    Next
    INDEX
    Explanations

    Short

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èvement
    0.36
     pesquis
    0.35
    骇
    0.34
     cousins
    0.34
    وانات
    0.34
    iclopedia
    0.34
     penas
    0.34
    ⑮
    0.34
     अपहरण
    0.33
    ंपरिक
    0.33
    POSITIVE LOGITS
     よ
    0.32
    Lopez
    0.31
    thro
    0.30
     Learners
    0.30
    උ
    0.30
     الحلو
    0.30
     Kre
    0.29
    }\}
    0.29
    iole
    0.29
    ∵
    0.29
    Activations Density 0.001%

    No Known Activations