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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5396
    Prev
    Next
    INDEX
    Explanations

    copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    sion
    1.38
    o
    1.27
    次
    1.20
    ﻭ
    1.19
    a
    1.16
    h
    1.16
     zák
    1.15
    oğlu
    1.13
     integrals
    1.13
    𝙖
    1.09
    POSITIVE LOGITS
    প্র
    1.28
    ح
    1.26
     enige
    1.19
    รง
    1.15
    时候
    1.15
    隣
    1.12
    ー
    1.09
     Оста
    1.04
    仕方
    1.03
     sparsely
    1.03
    Activations Density 0.001%

    No Known Activations