© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    NAND logic, Nanda Dynasty, human animals

    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
     Nxd
    2.73
    う
    2.65
     flanges
    2.60
    jLabel
    2.56
    ১৪
    2.50
    ется
    2.49
     flange
    2.45
     मातर
    2.42
    ১৯
    2.39
    ために
    2.39
    POSITIVE LOGITS
    𝙣
    2.83
    та
    2.81
    ্ড
    2.68
     bruge
    2.59
    ER
    2.51
     invo
    2.48
     twos
    2.46
    casa
    2.43
    𝒍
    2.42
    𝒈
    2.39
    Activations Density 0.017%

    No Known Activations