© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6668
    Prev
    Next
    INDEX
    Explanations

    mobile carriers

    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
    𝑐
    1.56
    𝑇
    1.45
    𝑏
    1.27
    ℎ
    1.26
    s
    1.26
    𝐺
    1.25
    𝐿
    1.24
    𝑡
    1.23
    𝑜
    1.23
    𝑈
    1.23
    POSITIVE LOGITS
    ва
    1.63
    م
    1.39
    ल
    1.34
    ein
    1.28
    fohlen
    1.28
    ed
    1.20
    ้
    1.15
    e
    1.15
    dain
    1.15
    ווי
    1.15
    Activations Density 0.001%

    No Known Activations