© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6163
    Prev
    Next
    INDEX
    Explanations

    py scripts and servers

    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
    س
    2.28
     Vgl
    2.12
    ératures
    2.11
    基金产品
    2.11
    ia
    2.09
    これで
    2.07
    ক
    2.05
    tä
    2.04
     ważne
    2.04
     بشكل
    2.02
    POSITIVE LOGITS
    yaa
    2.69
    ا
    2.57
    𝑬
    2.54
     depan
    2.48
    ați
    2.41
    ্লাহ
    2.38
    ियत
    2.38
    sor
    2.36
    midnight
    2.31
    ﻉ
    2.31
    Activations Density 0.000%

    No Known Activations