© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5685
    Prev
    Next
    INDEX
    Explanations

    corridors and hallways

    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
    不然
    2.88
    不喜欢
    2.48
     ideia
    2.44
    𝑎
    2.43
    ্ধ্য
    2.41
    ть
    2.38
     firstName
    2.38
    お客
    2.38
    𝑠
    2.34
    𝑑
    2.33
    POSITIVE LOGITS
    ^{'
    2.81
    㗊
    2.72
    fice
    2.68
     Vgl
    2.66
    বহ
    2.66
    Notwithstanding
    2.65
    MSE
    2.59
    өн
    2.55
    ricao
    2.54
    ના
    2.51
    Activations Density 0.002%

    No Known Activations