© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1180
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    િ
    2.21
    몽
    2.04
    و
    2.03
     excepción
    1.91
     Isabel
    1.89
     iglesia
    1.88
    гістра
    1.87
    िओ
    1.86
     embark
    1.84
    fü
    1.82
    POSITIVE LOGITS
    ن
    2.97
    वीं
    2.83
    cknowled
    2.37
     robbed
    2.36
    ﻉ
    2.34
    дентификаторы
    2.33
    ע
    2.32
     piensan
    2.32
    ያንዳ
    2.30
    सी
    2.30
    Activations Density 0.026%

    No Known Activations