© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197963
    Prev
    Next
    INDEX
    Explanations

    Exc

    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
     pus
    0.42
     bundle
    0.40
    мітки
    0.40
     facets
    0.40
     excuses
    0.40
     joy
    0.39
    iados
    0.38
    豺
    0.36
    祅
    0.35
     eks
    0.35
    POSITIVE LOGITS
    保温
    0.40
    hibition
    0.38
    طن
    0.38
    ﻅ
    0.38
    ആ
    0.38
     Archaeological
    0.37
     afirmó
    0.37
    Quem
    0.37
     Dahmer
    0.37
    temperature
    0.35
    Activations Density 0.001%

    No Known Activations