© 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. 6144
    Prev
    Next
    INDEX
    Explanations

    list comprehension

    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
    ating
    2.36
     greatest
    2.24
     minimal
    2.13
     behalf
    2.10
    ه‌ای
    2.09
    ﻟ
    2.07
     "";
    2.07
     submarines
    2.07
    াত
    2.05
    Vid
    2.03
    POSITIVE LOGITS
    া
    2.79
    ப்
    2.52
    一来
    2.38
     τις
    2.37
    की
    2.24
     químicos
    2.22
     особенностей
    2.19
    개를
    2.19
    𝒸
    2.17
     ዓይነ
    2.16
    Activations Density 0.021%

    No Known Activations