© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107633
    Prev
    Next
    INDEX
    Explanations

    multilingual text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    s
    1.38
    .
    1.36
    ק
    1.33
    ت
    1.31
    ه
    1.30
    س
    1.27
    it
    1.24
    사
    1.18
    n
    1.16
    ก็
    1.02
    POSITIVE LOGITS
     qué
    1.10
    на
    1.08
     macchina
    1.06
    ви
    1.02
     límite
    1.00
    ﻌ
    1.00
     письмо
    0.97
     développ
    0.96
     بي
    0.96
     savaş
    0.96
    Activations Density 0.000%

    No Known Activations