© 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. 5847
    Prev
    Next
    INDEX
    Explanations

    late 1800s and early 1900s

    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
    2.42
    л
    2.28
    lo
    2.23
    ли
    2.09
    र
    2.03
    ার
    2.02
    er
    2.00
    يا
    1.92
    lama
    1.91
    rg
    1.90
    POSITIVE LOGITS
    electrolyte
    2.28
    eenth
    2.26
     избежать
    2.23
    een
    2.08
    excluding
    2.07
     coinciding
    2.04
    ゚
    2.02
    aol
    2.02
    drinks
    2.00
    𝟏
    2.00
    Activations Density 0.038%

    No Known Activations