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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9722
    Prev
    Next
    INDEX
    Explanations

    actions or edits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Lutz
    0.76
    ﻢ
    0.74
     ترکیه
    0.74
     चाहिँ
    0.74
     Mỹ
    0.74
    ೩
    0.74
    slidesPerView
    0.72
     الأمريكية
    0.71
     आवेदक
    0.71
    ﺢ
    0.70
    POSITIVE LOGITS
     incre
    1.10
     remov
    1.09
    includ
    1.08
     Writ
    1.05
     coordin
    1.04
     restor
    1.04
     writ
    1.02
     becom
    1.01
     prepar
    0.99
     includ
    0.98
    Activations Density 0.106%

    No Known Activations