© 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. 4776
    Prev
    Next
    INDEX
    Explanations

    code and UI elements

    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
    er
    2.81
    ي
    2.73
    ি
    2.68
    い
    2.63
    ার
    2.55
    ोत्तम
    2.46
    𝐓
    2.44
    ᴛ
    2.44
    ました
    2.34
    ᴄ
    2.27
    POSITIVE LOGITS
    ー
    2.29
    ic
    2.13
    儁
    2.12
    Aub
    2.10
    ressing
    2.04
    berge
    2.02
     fiscale
    1.99
     sake
    1.97
    JlcG
    1.97
    Основ
    1.96
    Activations Density 0.001%

    No Known Activations