© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3382
    Prev
    Next
    INDEX
    Explanations

    quantities and ranges

    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_5_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
    ل
    1.24
     aí
    1.15
    l
    1.08
    एच
    1.00
    al
    0.98
    eks
    0.97
    ური
    0.95
     pasangan
    0.94
    d
    0.94
    ent
    0.94
    POSITIVE LOGITS
     dozen
    1.75
     ribu
    1.52
    dozen
    1.44
     centena
    1.44
     dozens
    1.43
    몇
    1.38
     hundred
    1.36
     centaines
    1.35
     thousand
    1.33
     поряд
    1.26
    Activations Density 0.183%

    No Known Activations