© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6113
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_44_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
     organizing
    0.39
     making
    0.38
    َا
    0.37
    ﻼ
    0.35
     organising
    0.34
     annex
    0.33
    جات
    0.33
     makes
    0.33
     PQ
    0.33
     Organizing
    0.33
    POSITIVE LOGITS
    ଵ
    0.35
     uuid
    0.33
     प्रेरित
    0.33
    Prefab
    0.33
     “[
    0.33
    Summit
    0.33
     Valor
    0.32
     UUID
    0.32
     ಸ್ಥ
    0.32
    ГУ
    0.31
    Activations Density 0.000%

    No Known Activations