© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 2925
    Prev
    Next
    INDEX
    Explanations

    physical aspects and conditions

    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_5_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
    ﺓ
    0.37
    égek
    0.34
    年的
    0.34
    eworthy
    0.34
    ﻯ
    0.32
    বেশী
    0.31
     IRE
    0.30
     heavyweight
    0.30
    ✯
    0.30
    hibition
    0.30
    POSITIVE LOGITS
     kinks
    0.33
    IEnumerable
    0.29
    c
    0.27
    chave
    0.27
    つ
    0.27
    n
    0.27
    `${
    0.26
    sung
    0.26
     timeouts
    0.26
     برم
    0.26
    Activations Density 0.331%

    No Known Activations