© 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. 4773
    Prev
    Next
    INDEX
    Explanations

    Augmented Generation

    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
    𝗹
    1.72
    𝗿
    1.43
    er
    1.42
    咐
    1.31
    erweise
    1.28
    Symptoms
    1.28
     стен
    1.26
    ̣c
    1.26
    𝗧
    1.25
    𝗴
    1.25
    POSITIVE LOGITS
    ্যান্ড
    1.48
    𝘬
    1.39
    ร์
    1.36
    س
    1.32
    Proceedings
    1.22
    ㅋ
    1.18
    ים
    1.17
    atir
    1.13
     tràn
    1.13
    нный
    1.11
    Activations Density 0.003%

    No Known Activations